Search

The goal of text-queried target sound extraction (TSE) is to extract from a mixture a sound source specified with a natural-language caption. While it is preferable to have access to large-scale text-audio pairs to address a variety of text prompts, the limited number of available high-quality text-audio pairs hinders the data scaling. To this end, this work explores how to leverage audio-only data without any captions for the text-queried TSE task to potentially scale up the data amount. A straightforward way to do so is to use a joint audio-text embedding model, such as the contrastive language-audio pre-training (CLAP) model, as a query encoder and train a TSE model using audio embeddings obtained from the ground-truth audio. The TSE model can then accept text queries at inference time by switching to the text encoder. While this approach should work if the audio and text embedding spaces in CLAP were well aligned, in practice, the embeddings have domain-specific information that causes the TSE model to overfit to audio queries. We investigate several methods to avoid overfitting and show that simple embedding-manipulation methods such as dropout can effectively alleviate this issue. Extensive experiments demonstrate that using audio-only data with embedding dropout is as effective as using text captions during training, and audio-only data can be effectively leveraged to improve text-queried TSE models., Comment: Submitted to ICASSP 2025

Reverberation as supervision (RAS) is a framework that allows for training monaural speech separation models from multi-channel mixtures in an unsupervised manner. In RAS, models are trained so that sources predicted from a mixture at an input channel can be mapped to reconstruct a mixture at a target channel. However, stable unsupervised training has so far only been achieved in over-determined source-channel conditions, leaving the key determined case unsolved. This work proposes enhanced RAS (ERAS) for solving this problem. Through qualitative analysis, we found that stable training can be achieved by leveraging the loss term to alleviate the frequency-permutation problem. Separation performance is also boosted by adding a novel loss term where separated signals mapped back to their own input mixture are used as pseudo-targets for the signals separated from other channels and mapped to the same channel. Experimental results demonstrate high stability and performance of ERAS., Comment: Accepted to Interspeech 2024

Time-frequency (TF) domain dual-path models achieve high-fidelity speech separation. While some previous state-of-the-art (SoTA) models rely on RNNs, this reliance means they lack the parallelizability, scalability, and versatility of Transformer blocks. Given the wide-ranging success of pure Transformer-based architectures in other fields, in this work we focus on removing the RNN from TF-domain dual-path models, while maintaining SoTA performance. This work presents TF-Locoformer, a Transformer-based model with LOcal-modeling by COnvolution. The model uses feed-forward networks (FFNs) with convolution layers, instead of linear layers, to capture local information, letting the self-attention focus on capturing global patterns. We place two such FFNs before and after self-attention to enhance the local-modeling capability. We also introduce a novel normalization for TF-domain dual-path models. Experiments on separation and enhancement datasets show that the proposed model meets or exceeds SoTA in multiple benchmarks with an RNN-free architecture., Comment: Accepted to IWAENC 2024

Sound event detection is the task of recognizing sounds and determining their extent (onset/offset times) within an audio clip. Existing systems commonly predict sound presence confidence in short time frames. Then, thresholding produces binary frame-level presence decisions, with the extent of individual events determined by merging consecutive positive frames. In this paper, we show that frame-level thresholding degrades the prediction of the event extent by coupling it with the system's sound presence confidence. We propose to decouple the prediction of event extent and confidence by introducing SEBBs, which format each sound event prediction as a tuple of a class type, extent, and overall confidence. We also propose a change-detection-based algorithm to convert legacy frame-level outputs into SEBBs. We find the algorithm significantly improves the performance of DCASE 2023 Challenge systems, boosting the state of the art from .644 to .686 PSDS1., Comment: Accepted for publication at Interspeech 2024

We introduce Self-Monitored Inference-Time INtervention (SMITIN), an approach for controlling an autoregressive generative music transformer using classifier probes. These simple logistic regression probes are trained on the output of each attention head in the transformer using a small dataset of audio examples both exhibiting and missing a specific musical trait (e.g., the presence/absence of drums, or real/synthetic music). We then steer the attention heads in the probe direction, ensuring the generative model output captures the desired musical trait. Additionally, we monitor the probe output to avoid adding an excessive amount of intervention into the autoregressive generation, which could lead to temporally incoherent music. We validate our results objectively and subjectively for both audio continuation and text-to-music applications, demonstrating the ability to add controls to large generative models for which retraining or even fine-tuning is impractical for most musicians. Audio samples of the proposed intervention approach are available on our demo page http://tinyurl.com/smitin .

In music source separation, a standard training data augmentation procedure is to create new training samples by randomly combining instrument stems from different songs. These random mixes have mismatched characteristics compared to real music, e.g., the different stems do not have consistent beat or tonality, resulting in a cacophony. In this work, we investigate why random mixing is effective when training a state-of-the-art music source separation model in spite of the apparent distribution shift it creates. Additionally, we examine why performance levels off despite potentially limitless combinations, and examine the sensitivity of music source separation performance to differences in beat and tonality of the instrumental sources in a mixture., Comment: ICASSP 2024 Workshop on Explainable AI for Speech and Audio

Head-related transfer functions (HRTFs) are important for immersive audio, and their spatial interpolation has been studied to upsample finite measurements. Recently, neural fields (NFs) which map from sound source direction to HRTF have gained attention. Existing NF-based methods focused on estimating the magnitude of the HRTF from a given sound source direction, and the magnitude is converted to a finite impulse response (FIR) filter. We propose the neural infinite impulse response filter field (NIIRF) method that instead estimates the coefficients of cascaded IIR filters. IIR filters mimic the modal nature of HRTFs, thus needing fewer coefficients to approximate them well compared to FIR filters. We find that our method can match the performance of existing NF-based methods on multiple datasets, even outperforming them when measurements are sparse. We also explore approaches to personalize the NF to a subject and experimentally find low-rank adaptation to be effective., Comment: Accepted to ICASSP 2024

Neuro-steered speaker extraction aims to extract the listener's brain-attended speech signal from a multi-talker speech signal, in which the attention is derived from the cortical activity. This activity is usually recorded using electroencephalography (EEG) devices. Though promising, current methods often have a high speaker confusion error, where the interfering speaker is extracted instead of the attended speaker, degrading the listening experience. In this work, we aim to reduce the speaker confusion error in the neuro-steered speaker extraction model through a jointly fine-tuned auxiliary auditory attention detection model. The latter reinforces the consistency between the extracted target speech signal and the EEG representation, and also improves the EEG representation. Experimental results show that the proposed network significantly outperforms the baseline in terms of speaker confusion and overall signal quality in two-talker scenarios.

Target speech extraction aims to extract, based on a given conditioning cue, a target speech signal that is corrupted by interfering sources, such as noise or competing speakers. Building upon the achievements of the state-of-the-art (SOTA) time-frequency speaker separation model TF-GridNet, we propose AV-GridNet, a visual-grounded variant that incorporates the face recording of a target speaker as a conditioning factor during the extraction process. Recognizing the inherent dissimilarities between speech and noise signals as interfering sources, we also propose SAV-GridNet, a scenario-aware model that identifies the type of interfering scenario first and then applies a dedicated expert model trained specifically for that scenario. Our proposed model achieves SOTA results on the second COG-MHEAR Audio-Visual Speech Enhancement Challenge, outperforming other models by a significant margin, objectively and in a listening test. We also perform an extensive analysis of the results under the two scenarios., Comment: Accepted by ASRU 2023

The introduction of audio latent diffusion models possessing the ability to generate realistic sound clips on demand from a text description has the potential to revolutionize how we work with audio. In this work, we make an initial attempt at understanding the inner workings of audio latent diffusion models by investigating how their audio outputs compare with the training data, similar to how a doctor auscultates a patient by listening to the sounds of their organs. Using text-to-audio latent diffusion models trained on the AudioCaps dataset, we systematically analyze memorization behavior as a function of training set size. We also evaluate different retrieval metrics for evidence of training data memorization, finding the similarity between mel spectrograms to be more robust in detecting matches than learned embedding vectors. In the process of analyzing memorization in audio latent diffusion models, we also discover a large amount of duplicated audio clips within the AudioCaps database., Comment: Submitted to ICASSP 2024

Automated audio captioning (AAC) aims to generate informative descriptions for various sounds from nature and/or human activities. In recent years, AAC has quickly attracted research interest, with state-of-the-art systems now relying on a sequence-to-sequence (seq2seq) backbone powered by strong models such as Transformers. Following the macro-trend of applied machine learning research, in this work, we strive to improve the performance of seq2seq AAC models by extensively leveraging pretrained models and large language models (LLMs). Specifically, we utilize BEATs to extract fine-grained audio features. Then, we employ Instructor LLM to fetch text embeddings of captions, and infuse their language-modality knowledge into BEATs audio features via an auxiliary InfoNCE loss function. Moreover, we propose a novel data augmentation method that uses ChatGPT to produce caption mix-ups (i.e., grammatical and compact combinations of two captions) which, together with the corresponding audio mixtures, increase not only the amount but also the complexity and diversity of training data. During inference, we propose to employ nucleus sampling and a hybrid reranking algorithm, which has not been explored in AAC research. Combining our efforts, our model achieves a new state-of-the-art 32.6 SPIDEr-FL score on the Clotho evaluation split, and wins the 2023 DCASE AAC challenge., Comment: ICASSP 2024 camera-ready paper. Winner of the DCASE 2023 Challenge Task 6A: Automated Audio Captioning (AAC)

This paper summarizes the cinematic demixing (CDX) track of the Sound Demixing Challenge 2023 (SDX'23). We provide a comprehensive summary of the challenge setup, detailing the structure of the competition and the datasets used. Especially, we detail CDXDB23, a new hidden dataset constructed from real movies that was used to rank the submissions. The paper also offers insights into the most successful approaches employed by participants. Compared to the cocktail-fork baseline, the best-performing system trained exclusively on the simulated Divide and Remaster (DnR) dataset achieved an improvement of 1.8 dB in SDR, whereas the top-performing system on the open leaderboard, where any data could be used for training, saw a significant improvement of 5.7 dB. A significant source of this improvement was making the simulated data better match real cinematic audio, which we further investigate in detail., Comment: Accepted for Transactions of the International Society for Music Information Retrieval

In spite of the progress in music source separation research, the small amount of publicly-available clean source data remains a constant limiting factor for performance. Thus, recent advances in self-supervised learning present a largely-unexplored opportunity for improving separation models by leveraging unlabelled music data. In this paper, we propose a self-supervised learning framework for music source separation inspired by the HuBERT speech representation model. We first investigate the potential impact of the original HuBERT model by inserting an adapted version of it into the well-known Demucs V2 time-domain separation model architecture. We then propose a time-frequency-domain self-supervised model, Pac-HuBERT (for primitive auditory clustering HuBERT), that we later use in combination with a Res-U-Net decoder for source separation. Pac-HuBERT uses primitive auditory features of music as unsupervised clustering labels to initialize the self-supervised pretraining process using the Free Music Archive (FMA) dataset. The resulting framework achieves better source-to-distortion ratio (SDR) performance on the MusDB18 test set than the original Demucs V2 and Res-U-Net models. We further demonstrate that it can boost performance with small amounts of supervised data. Ultimately, our proposed framework is an effective solution to the challenge of limited clean source data for music source separation., Comment: 5 pages, 2 figures, 3 tables

Since diarization and source separation of meeting data are closely related tasks, we here propose an approach to perform the two objectives jointly. It builds upon the target-speaker voice activity detection (TS-VAD) diarization approach, which assumes that initial speaker embeddings are available. We replace the final combined speaker activity estimation network of TS-VAD with a network that produces speaker activity estimates at a time-frequency resolution. Those act as masks for source extraction, either via masking or via beamforming. The technique can be applied both for single-channel and multi-channel input and, in both cases, achieves a new state-of-the-art word error rate (WER) on the LibriCSS meeting data recognition task. We further compute speaker-aware and speaker-agnostic WERs to isolate the contribution of diarization errors to the overall WER performance., Comment: Submitted to IEEE/ACM TASLP

Emulating the human ability to solve the cocktail party problem, i.e., focus on a source of interest in a complex acoustic scene, is a long standing goal of audio source separation research. Much of this research investigates separating speech from noise, speech from speech, musical instruments from each other, or sound events from each other. In this paper, we focus on the cocktail fork problem, which takes a three-pronged approach to source separation by separating an audio mixture such as a movie soundtrack or podcast into the three broad categories of speech, music, and sound effects (SFX - understood to include ambient noise and natural sound events). We benchmark the performance of several deep learning-based source separation models on this task and evaluate them with respect to simple objective measures such as signal-to-distortion ratio (SDR) as well as objective metrics that better correlate with human perception. Furthermore, we thoroughly evaluate how source separation can influence downstream transcription tasks. First, we investigate the task of activity detection on the three sources as a way to both further improve source separation and perform transcription. We formulate the transcription tasks as speech recognition for speech and audio tagging for music and SFX. We observe that, while the use of source separation estimates improves transcription performance in comparison to the original soundtrack, performance is still sub-optimal due to artifacts introduced by the separation process. Therefore, we thoroughly investigate how remixing of the three separated source stems at various relative levels can reduce artifacts and consequently improve the transcription performance. We find that remixing music and SFX interferences at a target SNR of 17.5 dB reduces speech recognition word error rate, and similar impact from remixing is observed for tagging music and SFX content., Comment: Submitted to IEEE TASLP (In review), 13 pages, 6 figures

We introduce a framework for audio source separation using embeddings on a hyperbolic manifold that compactly represent the hierarchical relationship between sound sources and time-frequency features. Inspired by recent successes modeling hierarchical relationships in text and images with hyperbolic embeddings, our algorithm obtains a hyperbolic embedding for each time-frequency bin of a mixture signal and estimates masks using hyperbolic softmax layers. On a synthetic dataset containing mixtures of multiple people talking and musical instruments playing, our hyperbolic model performed comparably to a Euclidean baseline in terms of source to distortion ratio, with stronger performance at low embedding dimensions. Furthermore, we find that time-frequency regions containing multiple overlapping sources are embedded towards the center (i.e., the most uncertain region) of the hyperbolic space, and we can use this certainty estimate to efficiently trade-off between artifact introduction and interference reduction when isolating individual sounds., Comment: Submitted to ICASSP 2023, Demo page: https://darius522.github.io/hyperbolic-audio-sep/

Traditional source separation approaches train deep neural network models end-to-end with all the data available at once by minimizing the empirical risk on the whole training set. On the inference side, after training the model, the user fetches a static computation graph and runs the full model on some specified observed mixture signal to get the estimated source signals. Additionally, many of those models consist of several basic processing blocks which are applied sequentially. We argue that we can significantly increase resource efficiency during both training and inference stages by reformulating a model's training and inference procedures as iterative mappings of latent signal representations. First, we can apply the same processing block more than once on its output to refine the input signal and consequently improve parameter efficiency. During training, we can follow a block-wise procedure which enables a reduction on memory requirements. Thus, one can train a very complicated network structure using significantly less computation compared to end-to-end training. During inference, we can dynamically adjust how many processing blocks and iterations of a specific block an input signal needs using a gating module.

This paper proposes reverberation as supervision (RAS), a novel unsupervised loss function for single-channel reverberant speech separation. Prior methods for unsupervised separation required the synthesis of mixtures of mixtures or assumed the existence of a teacher model, making them difficult to consider as potential methods explaining the emergence of separation abilities in an animal's auditory system. We assume the availability of two-channel mixtures at training time, and train a neural network to separate the sources given one of the channels as input such that the other channel may be predicted from the separated sources. As the relationship between the room impulse responses (RIRs) of each channel depends on the locations of the sources, which are unknown to the network, the network cannot rely on learning that relationship. Instead, our proposed loss function fits each of the separated sources to the mixture in the target channel via Wiener filtering, and compares the resulting mixture to the ground-truth one. We show that minimizing the scale-invariant signal-to-distortion ratio (SI-SDR) of the predicted right-channel mixture with respect to the ground truth implicitly guides the network towards separating the left-channel sources. On a semi-supervised reverberant speech separation task based on the WHAMR! dataset, using training data where just 5% (resp., 10%) of the mixtures are labeled with associated isolated sources, we achieve 70% (resp., 78%) of the SI-SDR improvement obtained when training with supervision on the full training set, while a model trained only on the labeled data obtains 43% (resp., 45%)., Comment: 5 pages, 2 figures, 4 tables. Submitted to ICASSP 2023

Deep neural state-space models (SSMs) provide a powerful tool for modeling dynamical systems solely using operational data. Typically, neural SSMs are trained using data collected from the actual system under consideration, despite the likely existence of operational data from similar systems which have previously been deployed in the field. In this paper, we propose the use of model-agnostic meta-learning (MAML) for constructing deep encoder network-based SSMs, by leveraging a combination of archived data from similar systems (used to meta-train offline) and limited data from the actual system (used for rapid online adaptation). We demonstrate using a numerical example that meta-learning can result in more accurate neural SSM models than supervised- or transfer-learning, despite few adaptation steps and limited online data. Additionally, we show that by carefully partitioning and adapting the encoder layers while fixing the state-transition operator, we can achieve comparable performance to MAML while reducing online adaptation complexity., Comment: Submitted for conference publication

Recent research has shown remarkable performance in leveraging multiple extraneous conditional and non-mutually exclusive semantic concepts for sound source separation, allowing the flexibility to extract a given target source based on multiple different queries. In this work, we propose a new optimal condition training (OCT) method for single-channel target source separation, based on greedy parameter updates using the highest performing condition among equivalent conditions associated with a given target source. Our experiments show that the complementary information carried by the diverse semantic concepts significantly helps to disentangle and isolate sources of interest much more efficiently compared to single-conditioned models. Moreover, we propose a variation of OCT with condition refinement, in which an initial conditional vector is adapted to the given mixture and transformed to a more amenable representation for target source extraction. We showcase the effectiveness of OCT on diverse source separation experiments where it improves upon permutation invariant models with oracle assignment and obtains state-of-the-art performance in the more challenging task of text-based source separation, outperforming even dedicated text-only conditioned models., Comment: Submitted to ICASSP 2023

Diffusion models have recently shown promising results for difficult enhancement tasks such as the conditional and unconditional restoration of natural images and audio signals. In this work, we explore the possibility of leveraging a recently proposed advanced iterative diffusion model, namely cold diffusion, to recover clean speech signals from noisy signals. The unique mathematical properties of the sampling process from cold diffusion could be utilized to restore high-quality samples from arbitrary degradations. Based on these properties, we propose an improved training algorithm and objective to help the model generalize better during the sampling process. We verify our proposed framework by investigating two model architectures. Experimental results on benchmark speech enhancement dataset VoiceBank-DEMAND demonstrate the strong performance of the proposed approach compared to representative discriminative models and diffusion-based enhancement models., Comment: 5 pages, 1 figure, 1 table, 3 algorithms. To appear in ICASSP 2023. With corrected references

Speaker diarization is well studied for constrained audios but little explored for challenging in-the-wild videos, which have more speakers, shorter utterances, and inconsistent on-screen speakers. We address this gap by proposing an audio-visual diarization model which combines audio-only and visual-centric sub-systems via late fusion. For audio, we show that an attractor-based end-to-end system (EEND-EDA) performs remarkably well when trained with our proposed recipe of a simulated proxy dataset, and propose an improved version, EEND-EDA++, that uses attention in decoding and a speaker recognition loss during training to better handle the larger number of speakers. The visual-centric sub-system leverages facial attributes and lip-audio synchrony for identity and speech activity estimation of on-screen speakers. Both sub-systems surpass the state of the art (SOTA) by a large margin, with the fused audio-visual system achieving a new SOTA on the AVA-AVD benchmark.

Deep learning based speech enhancement in the short-time Fourier transform (STFT) domain typically uses a large window length such as 32 ms. A larger window can lead to higher frequency resolution and potentially better enhancement. This however incurs an algorithmic latency of 32 ms in an online setup, because the overlap-add algorithm used in the inverse STFT (iSTFT) is also performed using the same window size. To reduce this inherent latency, we adapt a conventional dual-window-size approach, where a regular input window size is used for STFT but a shorter output window is used for overlap-add, for STFT-domain deep learning based frame-online speech enhancement. Based on this STFT-iSTFT configuration, we employ complex spectral mapping for frame-online enhancement, where a deep neural network (DNN) is trained to predict the real and imaginary (RI) components of target speech from the mixture RI components. In addition, we use the DNN-predicted RI components to conduct frame-online beamforming, the results of which are used as extra features for a second DNN to perform frame-online post-filtering. The frequency-domain beamformer can be easily integrated with our DNNs and is designed to not incur any algorithmic latency. Additionally, we propose a future-frame prediction technique to further reduce the algorithmic latency. Evaluation on noisy-reverberant speech enhancement shows the effectiveness of the proposed algorithms. Compared with Conv-TasNet, our STFT-domain system can achieve better enhancement performance for a comparable amount of computation, or comparable performance with less computation, maintaining strong performance at an algorithmic latency as low as 2 ms., Comment: in IEEE/ACM Transactions on Audio, Speech, and Language Processing

We introduce a new paradigm for single-channel target source separation where the sources of interest can be distinguished using non-mutually exclusive concepts (e.g., loudness, gender, language, spatial location, etc). Our proposed heterogeneous separation framework can seamlessly leverage datasets with large distribution shifts and learn cross-domain representations under a variety of concepts used as conditioning. Our experiments show that training separation models with heterogeneous conditions facilitates the generalization to new concepts with unseen out-of-domain data while also performing substantially higher than single-domain specialist models. Notably, such training leads to more robust learning of new harder source separation discriminative concepts and can yield improvements over permutation invariant training with oracle source selection. We analyze the intrinsic behavior of source separation training with heterogeneous metadata and propose ways to alleviate emerging problems with challenging separation conditions. We release the collection of preparation recipes for all datasets used to further promote research towards this challenging task., Comment: Submitted to Interspeech 2022

Existing systems for sound event localization and detection (SELD) typically operate by estimating a source location for all classes at every time instant. In this paper, we propose an alternative class-conditioned SELD model for situations where we may not be interested in localizing all classes all of the time. This class-conditioned SELD model takes as input the spatial and spectral features from the sound file, and also a one-hot vector indicating the class we are currently interested in localizing. We inject the conditioning information at several points in our model using feature-wise linear modulation (FiLM) layers. Through experiments on the DCASE 2020 Task 3 dataset, we show that the proposed class-conditioned SELD model performs better in terms of common SELD metrics than the baseline model that locates all classes simultaneously, and also outperforms specialist models that are trained to locate only a single class of interest. We also evaluate performance on the DCASE 2021 Task 3 dataset, which includes directional interference (sound events from classes we are not interested in localizing) and notice especially strong improvement from the class-conditioned model., Comment: Accepted for publication at ICASSP 2022

The cocktail party problem aims at isolating any source of interest within a complex acoustic scene, and has long inspired audio source separation research. Recent efforts have mainly focused on separating speech from noise, speech from speech, musical instruments from each other, or sound events from each other. However, separating an audio mixture (e.g., movie soundtrack) into the three broad categories of speech, music, and sound effects (understood to include ambient noise and natural sound events) has been left largely unexplored, despite a wide range of potential applications. This paper formalizes this task as the cocktail fork problem, and presents the Divide and Remaster (DnR) dataset to foster research on this topic. DnR is built from three well-established audio datasets (LibriSpeech, FMA, FSD50k), taking care to reproduce conditions similar to professionally produced content in terms of source overlap and relative loudness, and made available at CD quality. We benchmark standard source separation algorithms on DnR, and further introduce a new multi-resolution model to better address the variety of acoustic characteristics of the three source types. Our best model produces SI-SDR improvements over the mixture of 11.0 dB for music, 11.2 dB for speech, and 10.8 dB for sound effects., Comment: Accepted to ICASSP2022. For resources and examples, see https://cocktail-fork.github.io

A promising approach for multi-microphone speech separation involves two deep neural networks (DNN), where the predicted target speech from the first DNN is used to compute signal statistics for time-invariant minimum variance distortionless response (MVDR) beamforming, and the MVDR result is then used as extra features for the second DNN to predict target speech. Previous studies suggested that the MVDR result can provide complementary information for the second DNN to better predict target speech. However, on fixed-geometry arrays, both DNNs can take in, for example, the real and imaginary (RI) components of the multi-channel mixture as features to leverage the spatial and spectral information for enhancement. It is not explained clearly why the linear MVDR result can be complementary and why it is still needed, considering that the DNNs and the beamformer use the same input, and the DNNs perform non-linear filtering and could render the linear filtering of MVDR unnecessary. Similarly, in monaural cases, one can replace the MVDR beamformer with a monaural weighted prediction error (WPE) filter. Although the linear WPE filter and the DNNs use the same mixture RI components as input, the WPE result is found to significantly improve the second DNN. This study provides a novel explanation from the perspective of the low-distortion nature of such algorithms, and finds that they can consistently improve phase estimation. Equipped with this understanding, we investigate several low-distortion target estimation algorithms including several beamformers, WPE, forward convolutive prediction, and their combinations, and use their results as extra features to train the second network to achieve better enhancement. Evaluation results on single- and multi-microphone speech dereverberation and enhancement tasks indicate the effectiveness of the proposed approach, and the validity of the proposed view., Comment: in submission

A promising approach for speech dereverberation is based on supervised learning, where a deep neural network (DNN) is trained to predict the direct sound from noisy-reverberant speech. This data-driven approach is based on leveraging prior knowledge of clean speech patterns and seldom explicitly exploits the linear-filter structure in reverberation, i.e., that reverberation results from a linear convolution between a room impulse response (RIR) and a dry source signal. In this work, we propose to exploit this linear-filter structure within a deep learning based monaural speech dereverberation framework. The key idea is to first estimate the direct-path signal of the target speaker using a DNN and then identify signals that are decayed and delayed copies of the estimated direct-path signal, as these can be reliably considered as reverberation. They can be either directly removed for dereverberation, or used as extra features for another DNN to perform better dereverberation. To identify the copies, we estimate the underlying filter (or RIR) by efficiently solving a linear regression problem per frequency in the time-frequency domain. We then modify the proposed algorithm for speaker separation in reverberant and noisy-reverberant conditions. State-of-the-art speech dereverberation and speaker separation results are obtained on the REVERB, SMS-WSJ, and WHAMR! datasets., Comment: in IEEE/ACM Transactions on Audio, Speech, and Language Processing

We investigate the effectiveness of convolutive prediction, a novel formulation of linear prediction for speech dereverberation, for speaker separation in reverberant conditions. The key idea is to first use a deep neural network (DNN) to estimate the direct-path signal of each speaker, and then identify delayed and decayed copies of the estimated direct-path signal. Such copies are likely due to reverberation, and can be directly removed for dereverberation or used as extra features for another DNN to perform better dereverberation and separation. To identify such copies, we solve a linear regression problem per frequency efficiently in the time-frequency (T-F) domain to estimate the underlying room impulse response (RIR). In the multi-channel extension, we perform minimum variance distortionless response (MVDR) beamforming on the outputs of convolutive prediction. The beamforming and dereverberation results are used as extra features for a second DNN to perform better separation and dereverberation. State-of-the-art results are obtained on the SMS-WSJ corpus., Comment: in IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), 2021

Deep neural network (DNN) based end-to-end optimization in the complex time-frequency (T-F) domain or time domain has shown considerable potential in monaural speech separation. Many recent studies optimize loss functions defined solely in the time or complex domain, without including a loss on magnitude. Although such loss functions typically produce better scores if the evaluation metrics are objective time-domain metrics, they however produce worse scores on speech quality and intelligibility metrics and usually lead to worse speech recognition performance, compared with including a loss on magnitude. While this phenomenon has been experimentally observed by many studies, it is often not accurately explained and there lacks a thorough understanding on its fundamental cause. This paper provides a novel view from the perspective of the implicit compensation between estimated magnitude and phase. Analytical results based on monaural speech separation and robust automatic speech recognition (ASR) tasks in noisy-reverberant conditions support the validity of our view., Comment: in IEEE Signal Processing Letters

Physics-informed dynamical system models form critical components of digital twins of the built environment. These digital twins enable the design of energy-efficient infrastructure, but must be properly calibrated to accurately reflect system behavior for downstream prediction and analysis. Dynamical system models of modern buildings are typically described by a large number of parameters and incur significant computational expenditure during simulations. To handle large-scale calibration of digital twins without exorbitant simulations, we propose ANP-BBO: a scalable and parallelizable batch-wise Bayesian optimization (BBO) methodology that leverages attentive neural processes (ANPs)., Comment: 12 pages, accepted to ICML 2021 Workshop on Tackling Climate Change with Machine Learning

Most music source separation systems require large collections of isolated sources for training, which can be difficult to obtain. In this work, we use musical scores, which are comparatively easy to obtain, as a weak label for training a source separation system. In contrast with previous score-informed separation approaches, our system does not require isolated sources, and score is used only as a training target, not required for inference. Our model consists of a separator that outputs a time-frequency mask for each instrument, and a transcriptor that acts as a critic, providing both temporal and frequency supervision to guide the learning of the separator. A harmonic mask constraint is introduced as another way of leveraging score information during training, and we propose two novel adversarial losses for additional fine-tuning of both the transcriptor and the separator. Results demonstrate that using score information outperforms temporal weak-labels, and adversarial structures lead to further improvements in both separation and transcription performance.

Clipping the gradient is a known approach to improving gradient descent, but requires hand selection of a clipping threshold hyperparameter. We present AutoClip, a simple method for automatically and adaptively choosing a gradient clipping threshold, based on the history of gradient norms observed during training. Experimental results show that applying AutoClip results in improved generalization performance for audio source separation networks. Observation of the training dynamics of a separation network trained with and without AutoClip show that AutoClip guides optimization into smoother parts of the loss landscape. AutoClip is very simple to implement and can be integrated readily into a variety of applications across multiple domains., Comment: Accepted at 2020 IEEE International Workshop on Machine Learning for Signal Processing, Sept.\ 21--24, 2020, Espoo, Finland

While there has been much recent progress using deep learning techniques to separate speech and music audio signals, these systems typically require large collections of isolated sources during the training process. When extending audio source separation algorithms to more general domains such as environmental monitoring, it may not be possible to obtain isolated signals for training. Here, we propose objective functions and network architectures that enable training a source separation system with weak labels. In this scenario, weak labels are defined in contrast with strong time-frequency (TF) labels such as those obtained from isolated sources, and refer either to frame-level weak labels where one only has access to the time periods when different sources are active in an audio mixture, or to clip-level weak labels that only indicate the presence or absence of sounds in an entire audio clip. We train a separator that estimates a TF mask for each type of sound event, using a sound event classifier as an assessor of the separator's performance to bridge the gap between the TF-level separation and the ground truth weak labels only available at the frame or clip level. Our objective function requires the classifier applied to a separated source to assign high probability to the class corresponding to that source and low probability to all other classes. The objective function also enforces that the separated sources sum up to the mixture. We benchmark the performance of our algorithm using synthetic mixtures of overlapping events created from a database of sounds recorded in urban environments. Compared to training a network using isolated sources, our model achieves somewhat lower but still significant SI-SDR improvement, even in scenarios with significant sound event overlap.

Separating an audio scene such as a cocktail party into constituent, meaningful components is a core task in computer audition. Deep networks are the state-of-the-art approach. They are trained on synthetic mixtures of audio made from isolated sound source recordings so that ground truth for the separation is known. However, the vast majority of available audio is not isolated. The brain uses primitive cues that are independent of the characteristics of any particular sound source to perform an initial segmentation of the audio scene. We present a method for bootstrapping a deep model for music source separation without ground truth by using multiple primitive cues. We apply our method to train a network on a large set of unlabeled music recordings from YouTube to separate vocals from accompaniment without the need for ground truth isolated sources or artificial training mixtures.

While significant advances have been made with respect to the separation of overlapping speech signals, studies have been largely constrained to mixtures of clean, near anechoic speech, not representative of many real-world scenarios. Although the WHAM! dataset introduced noise to the ubiquitous wsj0-2mix dataset, it did not include reverberation, which is generally present in indoor recordings outside of recording studios. The spectral smearing caused by reverberation can result in significant performance degradation for standard deep learning-based speech separation systems, which rely on spectral structure and the sparsity of speech signals to tease apart sources. To address this, we introduce WHAMR!, an augmented version of WHAM! with synthetic reverberated sources, and provide a thorough baseline analysis of current techniques as well as novel cascaded architectures on the newly introduced conditions., Comment: Accepted for publication at ICASSP 2020

Music source separation performance has greatly improved in recent years with the advent of approaches based on deep learning. Such methods typically require large amounts of labelled training data, which in the case of music consist of mixtures and corresponding instrument stems. However, stems are unavailable for most commercial music, and only limited datasets have so far been released to the public. It can thus be difficult to draw conclusions when comparing various source separation methods, as the difference in performance may stem as much from better data augmentation techniques or training tricks to alleviate the limited availability of training data, as from intrinsically better model architectures and objective functions. In this paper, we present the synthesized Lakh dataset (Slakh) as a new tool for music source separation research. Slakh consists of high-quality renderings of instrumental mixtures and corresponding stems generated from the Lakh MIDI dataset (LMD) using professional-grade sample-based virtual instruments. A first version, Slakh2100, focuses on 2100 songs, resulting in 145 hours of mixtures. While not fully comparable because it is purely instrumental, this dataset contains an order of magnitude more data than MUSDB18, the {\it de facto} standard dataset in the field. We show that Slakh can be used to effectively augment existing datasets for musical instrument separation, while opening the door to a wide array of data-intensive music signal analysis tasks., Comment: Accepted for publication at WASPAA 2019

Recent progress in separating the speech signals from multiple overlapping speakers using a single audio channel has brought us closer to solving the cocktail party problem. However, most studies in this area use a constrained problem setup, comparing performance when speakers overlap almost completely, at artificially low sampling rates, and with no external background noise. In this paper, we strive to move the field towards more realistic and challenging scenarios. To that end, we created the WSJ0 Hipster Ambient Mixtures (WHAM!) dataset, consisting of two speaker mixtures from the wsj0-2mix dataset combined with real ambient noise samples. The samples were collected in coffee shops, restaurants, and bars in the San Francisco Bay Area, and are made publicly available. We benchmark various speech separation architectures and objective functions to evaluate their robustness to noise. While separation performance decreases as a result of noise, we still observe substantial gains relative to the noisy signals for most approaches., Comment: Accepted for publication at Interspeech 2019

Isolating individual instruments in a musical mixture has a myriad of potential applications, and seems imminently achievable given the levels of performance reached by recent deep learning methods. While most musical source separation techniques learn an independent model for each instrument, we propose using a common embedding space for the time-frequency bins of all instruments in a mixture inspired by deep clustering and deep attractor networks. Additionally, an auxiliary network is used to generate parameters of a Gaussian mixture model (GMM) where the posterior distribution over GMM components in the embedding space can be used to create a mask that separates individual sources from a mixture. In addition to outperforming a mask-inference baseline on the MUSDB-18 dataset, our embedding space is easily interpretable and can be used for query-based separation., Comment: 5 pages

Separating an audio scene into isolated sources is a fundamental problem in computer audition, analogous to image segmentation in visual scene analysis. Source separation systems based on deep learning are currently the most successful approaches for solving the underdetermined separation problem, where there are more sources than channels. Traditionally, such systems are trained on sound mixtures where the ground truth decomposition is already known. Since most real-world recordings do not have such a decomposition available, this limits the range of mixtures one can train on, and the range of mixtures the learned models may successfully separate. In this work, we use a simple blind spatial source separation algorithm to generate estimated decompositions of stereo mixtures. These estimates, together with a weighting scheme in the time-frequency domain, based on confidence in the separation quality, are used to train a deep learning model that can be used for single-channel separation, where no source direction information is available. This demonstrates how a simple cue such as the direction of origin of source can be used to bootstrap a model for source separation that can be used in situations where that cue is not available., Comment: 5 pages, 2 figures

Deep learning based speech enhancement and source separation systems have recently reached unprecedented levels of quality, to the point that performance is reaching a new ceiling. Most systems rely on estimating the magnitude of a target source by estimating a real-valued mask to be applied to a time-frequency representation of the mixture signal. A limiting factor in such approaches is a lack of phase estimation: the phase of the mixture is most often used when reconstructing the estimated time-domain signal. Here, we propose "magbook", "phasebook", and "combook", three new types of layers based on discrete representations that can be used to estimate complex time-frequency masks. Magbook layers extend classical sigmoidal units and a recently introduced convex softmax activation for mask-based magnitude estimation. Phasebook layers use a similar structure to give an estimate of the phase mask without suffering from phase wrapping issues. Combook layers are an alternative to the magbook-phasebook combination that directly estimate complex masks. We present various training and inference schemes involving these representations, and explain in particular how to include them in an end-to-end learning framework. We also present an oracle study to assess upper bounds on performance for various types of masks using discrete phase representations. We evaluate the proposed methods on the wsj0-2mix dataset, a well-studied corpus for single-channel speaker-independent speaker separation, matching the performance of state-of-the-art mask-based approaches without requiring additional phase reconstruction steps.

Dialog systems need to understand dynamic visual scenes in order to have conversations with users about the objects and events around them. Scene-aware dialog systems for real-world applications could be developed by integrating state-of-the-art technologies from multiple research areas, including: end-to-end dialog technologies, which generate system responses using models trained from dialog data; visual question answering (VQA) technologies, which answer questions about images using learned image features; and video description technologies, in which descriptions/captions are generated from videos using multimodal information. We introduce a new dataset of dialogs about videos of human behaviors. Each dialog is a typed conversation that consists of a sequence of 10 question-and-answer(QA) pairs between two Amazon Mechanical Turk (AMT) workers. In total, we collected dialogs on roughly 9,000 videos. Using this new dataset for Audio Visual Scene-aware dialog (AVSD), we trained an end-to-end conversation model that generates responses in a dialog about a video. Our experiments demonstrate that using multimodal features that were developed for multimodal attention-based video description enhances the quality of generated dialog about dynamic scenes (videos). Our dataset, model code and pretrained models will be publicly available for a new Video Scene-Aware Dialog challenge., Comment: A prototype system for the Audio Visual Scene-aware Dialog (AVSD) at DSTC7