Search

Voice-to-MIDI real-time conversion is a challenging problem that comes with a series of obstacles and complications. The main issue is the tracking of the human voice pitch. Extracting the voice fundamental frequency can be inaccurate and highly computationally exacting due to the spectral complexity of voice signals. In addition, on account of microphone usage, the presence of environmental noise can further affect voice processing. An analysis of the current research and status of the market shows a plethora of voice-to-MIDI implementations revolving around the processing of audio signals deriving from microphones. This paper addresses the above-mentioned issues by implementing a novel experimental method where electroglottography is employed instead of microphones as a source for pitch-tracking. In the proposed system, the signal is processed and converted through an embedded hardware device. The use of electroglottography improves both the accuracy of pitch evaluation and the ease of voice information processing; firstly, it provides a direct measurement of the vocal folds' activity and, secondly, it bypasses the interferences caused by external sound sources. This allows the extraction of a simpler and cleaner signal that yields a more effective evaluation of the fundamental frequency during phonation. The proposed method delivers a faster and less computationally demanding conversion thus in turn, allowing for an efficacious real-time voice-to-MIDI conversion.

This paper describes the human information behaviours of long-time users of voice assistants or chatbot software that focuses on voice interaction to retrieve information, and which operate on technologies that use artificial intelligence to understand and act upon the information requests of the user through a conversational interface. The paper reports on a case study based on 10 interviews with adult participants who have used voice assistants in their homes for at least six months. Interviews were semi-structured and focused on connecting to the users' and their family's experiences of using voice assistants in their daily lives. Insights from our findings focus on two areas, how the humanness of voice assistants and their perceived personality affect information retrieval, and secondly, the difficulties in transitioning from text-based information seeking to speech-based interactions. This paper makes a case for expanding human information behaviour studies to include interactive conversational information retrieval devices such as voice assistants. [ABSTRACT FROM AUTHOR]

The acts of speaking and singing are different phenomena displaying distinct characteristics. The classification and distinction of these voice acts is vastly approached utilizing voice audio recordings and microphones. The use of audio recordings, however, can become challenging and computationally expensive due to the complexity of the voice signal. The research presented in this paper seeks to address this issue by implementing a deep learning classifier of speaking and singing voices based on bioimpedance measurement in replacement of audio recordings. In addition, the proposed research aims to develop a real-time voice act classification for the integration with voice-to-MIDI conversion. For such purposes, a system was designed, implemented, and tested using electroglottographic signals, Mel Frequency Cepstral Coefficients, and a deep neural network. The lack of datasets for the training of the model was tackled by creating a dedicated dataset 7200 bioimpedance measurement of both singing and speaking. The use of bioimpedance measurements allows to deliver high classification accuracy whilst keeping low computational needs for both preprocessing and classification. These characteristics, in turn, allows a fast deployment of the system for near-real-time applications. After the training, the system was broadly tested achieving a testing accuracy of 92% to 94%., (Copyright © 2023 The Authors. Published by Elsevier Inc. All rights reserved.)

Spoken term detection (STD) is a key technology for retrieval of spoken content, which will be very important to retrieve and browse multimedia content over the Internet. The discriminative capability of machine learning methods has recently been used to facilitate STD. This paper presents a new approach to improve STD using support vector machines (SVM) based on acoustic information. The concept of pseudo-relevance feedback (PRF) well used in the retrieval of text, image and video is used here. The basic idea of using PRF here is to assume some spoken segments in the first-pass retrieved results are relevant (or pseudo-relevant) and some others irrelevant (or pseudo-irrelevant), and take these segments as positive and negative examples to train a query-specific SVM. This SVM is then used for re-ranking the first-pass retrieved results, and only the re-ranked results are shown to the user. In this paper, feature vectors representing the spoken segments based on acoustic information to be used in SVM are considered and analyzed. Furthermore, conventionally in PRF the items with the highest and lowest scores in the first-pass retrieved results are respectively taken as pseudo-relevant and -irrelevant, but in this way some incorrect examples are inevitably included in the training data especially when the recognition accuracy is poor. Here we further propose an enhanced SVM which not only better selects positive/negative examples considering the reliability of the spoken segments, but emphasizes more on more reliable training examples by modifying the SVM formulation. Experiments on two different sets of spoken archives with different speaking styles and different levels of recognition accuracies demonstrated significant improvements offered by the proposed approaches. [ABSTRACT FROM PUBLISHER]

Spoken documents are audio signals and are thus not easily displayed on-screen and not easily scanned and browsed by the user. It is therefore highly desirable to automatically construct summaries, titles, latent topic trees and key term-based topic labels for these spoken documents to aid the user in browsing. We refer to this as semantic analysis and organization. Also, as network content is both copious and dynamic, with topics and domains changing everyday, the approaches here must be primarily unsupervised. We propose a framework for unsupervised semantic analysis and organization of spoken documents and for this purpose propose two measures derived from latent topic analysis: latent topic significance and latent topic entropy. We show that these can be integrated into an application system, with which the user can more easily navigate archives of spoken documents. Probabilistic latent semantic analysis is used as a typical example approach for unsupervised topic analysis in most experiments, although latent Dirichlet allocation is also used in some experiments to show that the proposed measures are equally applicable for different analysis approaches. All of the experiments were performed on Mandarin Chinese broadcast news. [ABSTRACT FROM PUBLISHER]

Lattice-based speech indexing approaches are attractive for the combination of short spoken segments, short queries, and low automatic speech recognition (ASR) accuracies, as lattices provide recognition alternatives and therefore tend to compensate for recognition errors. Position-specific posterior lattices (PSPLs) and confusion networks (CNs), two of the most popular lattice-based approaches, both reduce disk space requirements and are more efficient than raw lattices. When PSPLs and CNs are used in a word-based fashion, they cannot handle OOV or rare word queries. In this paper, we propose an efficient approach for the construction of subword-based PSPLs (S-PSPLs) and CNs (S-CNs) and present a comprehensive performance analysis of PSPL and CN structures using both words and subword units, taking into account basic principles and structures, and supported by experimental results on Mandarin Chinese. S-PSPLs and S-CNs are shown to yield significant mean average precision (MAP) improvements over word-based PSPLs and CNs for both out-of-vocabulary (OOV) and in-vocabulary queries while requiring much less disk space for indexing. [ABSTRACT FROM PUBLISHER]

Detection of edit disfluencies is key to transcribing spontaneous utterances. In this paper, we present improved features and models to detect edit disfluencies and enhance transcription of spontaneous Mandarin speech using hypothesized disfluency interruption points (IPs) and edit word detection. A comprehensive set of prosodic features that takes into account the special characteristics of edit disfluencies in Mandarin is developed, and an improved model combining decision trees and maximum entropy is proposed to detect IPs. This model is further adapted to desired prosodic conditions by latent prosodic modeling, a probabilistic framework for analyzing speech prosody in terms of a set of latent prosodic states. These techniques contribute to higher recognition accuracy (by rescoring with the hypothesized IPs) and better edit word detection (using conditional random fields defined on Chinese characters) in the final transcription, as verified by experiments on a spontaneous Mandarin speech corpus. [ABSTRACT FROM AUTHOR]

In a distributed speech recognition (DSR) framework, the speech features are quantized and compressed at the client and recognized at the server. However, recognition accuracy is degraded by environmental noise at the input, quantization distortion, and transmission errors. In this paper, histogram-based quantization (HQ) is proposed, in which the partition cells for quantization are dynamically defined by the histogram or order statistics of a segment of the most recent past values of the parameter to be quantized. This scheme is shown to be able to solve to a good degree many problems related to DSR, A joint uncertainty decoding (JUD) approach is further developed to consider the uncertainty caused by both environmental noise and quantization errors. A three-stage error concealment (EC) framework is also developed to handle transmission errors. The proposed HQ is shown to be an attractive feature transformation approach for robust speech recognition outside of a DSR environment as well. All the claims have been verified by experiments using the Aurora 2 testing environment, and significant performance improvements for both robust and/or distributed speech recognition over conventional approaches have been achieved. [ABSTRACT FROM AUTHOR]

Multiple-pronunciation dictionaries have been found to be useful in pronunciation modeling for speech recognition. However, the extra pronunciation variants added in the dictionary inevitably increase the confusion among different words during recognition, and consequently limit the achievable improvements in the recognition performance. This paper proposes a three-stage framework for Mandarin Chinese to construct automatically the multiple-pronunciation dictionary while reducing the possible confusion caused. The proposed framework includes pronunciation generation (Stage 1), ranking (Stage 2) and pruning (Stage 3). New measures of confusability for multiple-pronunciation dictionaries were developed and shown to have a very strong correlation with recognition performance. With the proposed framework, it was shown that the confusability as measured can be reduced and recognition performance improved stage by stage. All of the above findings were verified by a series of experiments performed on both planned (LDC HUB-4NE) and spontaneous (LDC CALL-HOME) Mandarin Chinese speech corpora. [ABSTRACT FROM AUTHOR]

The singular value decomposition (SVD)-based method for single-channel speech enhancement has been shown to be very useful when the additive noise is white. For colored noise, with this approach, one needs to whiten the noise spectrum prior to SVD-based approach and perform the inverse whitening processing afterwards. A truncated quotient SVD (QSVD)-based approach has been proposed to handle this problem and found very useful. In this paper, a generalized SVD (GSVD)-based subspace approach for speech enhancement is first extended from the concept of the truncated QSVD-based approach, in which the dimension of the signal subspace can be precisely and automatically determined for each frame of the noisy signal. But with this new approach some residual noise is still perceivable under lower signal-to-noise ratio conditions. Therefore a perceptually constrained GSVD (PCGSVD)-based approach is further proposed to incorporate the masking properties of human auditory system to make sure the undesired residual noise to be nearly un-perceivable. Closed-form solutions are obtained for both the GSVD- and PCGSVD-based enhancement approaches. Very carefully performed objective evaluations and subjective listening tests show that the PCGSVD-based approach proposed here can offer improved speech quality, intelligibility and recognition accuracy, whether the noise is stationary or nonstationary, especially when the additive noise is nonwhite. [ABSTRACT FROM AUTHOR]

Eigenvoice techniques have been proposed to provide rapid speaker adaptation with very limited adaptation data, but the performance may be saturated when more adaptation data become available. This is because in these techniques an eigenspace with reduced dimensionality is established by properly utilizing the a priori knowledge from the large quantity of training data. The reduced dimensionality of the eigenspace requires less adaptation data to estimate the model parameters for the new speaker, but also makes it less easy to obtain more precise models with more adaptation data. In this paper, a new segmental eigenvoice approach is proposed, in which the eigenspace can be further segmented into N subeigenspaces by properly classifying the model parameters into N clusters. These N subeigenspaces can help to construct a more delicate eigenspace and more precise models when more adaptation data are available. It will be shown that there can be at least mixture-based, model-based and feature-based segmental eigenvoice approaches. Not only improved performance can be obtained, but these different approaches can be properly integrated to offer better performance. Two further approaches leading to improved segmental eigenvoice techniques with even better performance are also proposed. The experiments were performed with both a large vocabulary and a small vocabulary recognition tasks. [ABSTRACT FROM AUTHOR]

Specifics of hidden Markov model‐based speech recognition are investigated. Influence of modeling simple and context‐dependent phones, using simple Gaussian, two and three‐component Gaussian mixture probability density functions for modeling feature distribution, and incorporating language model are discussed. Word recognition rates and model complexity criteria are used for evaluating suitability of these modifications for practical applications. Development of large vocabulary continuous speech recognition system using HTK toolkit and WSJCAM0 English speech corpus is described. Results of experimental investigations are presented. [ABSTRACT FROM AUTHOR]

The increasing demand for communication services, coupled with recent technological advances in communication media and switching techniques, has resulted in a proliferation of new and expanded services. Currently, networks are needed which can transmit voice, data and video services in an application-independent fashion. Unified approaches employ a single switching technique across the entire network bandwidth, thus allowing services to be switched in an application-independent manner. This paper presents a taxonomy of integrated-service networks, including a look at NISDN, while focusing on unified approaches to integrated-service networks. The two most promising unified approaches are burst and fast packet switching. Burst switching is a circuit switching-based approach which allocates channel bandwidth to a connection only during the transmission of 'bursts' of information. Fast packet switching is a packet switching-based approach which can be characterized by very high transmission rates on network links and simple, hard-wired protocols which match the rapid channel speed of the network. Both approaches are being proposed as possible implementations for integrated-service networks. We survey these two approaches, and also examine the key performance issues found in fast packet switching. We then present the results of a simulation study of a fast packet switching network. [ABSTRACT FROM AUTHOR]