385 results on '"Hain, Thomas"'
Search Results
52. WINVC: One-Shot Voice Conversion with Weight Adaptive Instance Normalization
53. Use of Speaker Metadata for Improving Automatic Pronunciation Assessment
54. Multi-CMGAN+/+: Leveraging Multi-Objective Speech Quality Metric Prediction for Speech Enhancement
55. SCORE: Self-Supervised Correspondence Fine-Tuning for Improved Content Representations
56. Progressive Unsupervised Domain Adaptation for ASR Using Ensemble Models and Multi-Stage Training
57. Combining Conformer and Dual-Path-Transformer Networks for Single Channel Noisy Reverberant Speech Separation
58. Non-Intrusive Speech Intelligibility Prediction for Hearing-Impaired Users Using Intermediate ASR Features and Human Memory Models
59. H-VECTORS: Improving the robustness in utterance-level speaker embeddings using a hierarchical attention model
60. Automatic Genre and Show Identification of Broadcast Media
61. The 2015 Sheffield System for Transcription of Multi-Genre Broadcast Media
62. Latent Dirichlet Allocation Based Organisation of Broadcast Media Archives for Deep Neural Network Adaptation
63. Background-tracking Acoustic Features for Genre Identification of Broadcast Shows
64. The USFD Spoken Language Translation System for IWSLT 2014
65. Data-selective Transfer Learning for Multi-Domain Speech Recognition
66. Unsupervised Domain Discovery using Latent Dirichlet Allocation for Acoustic Modelling in Speech Recognition
67. On Time Domain Conformer Models for Monaural Speech Separation in Noisy Reverberant Acoustic Environments
68. Simulation of Teacher-Learner Interaction in English Language Pronunciation Learning
69. Deriving Translational Acoustic Sub-Word Embeddings
70. MUST: A Multilingual Student-Teacher Learning Approach for Low-Resource Speech Recognition
71. Evaluation of the effectiveness and efficiency of state-of-the-art features and models for automatic speech recognition error detection
72. Die Unternehmensgruppe Nassauische Heimstätte/Wohnstadt als Beispiel für eine zukunftsweisende Orientierung im Wohnungsbau
73. Energieeffizienz, Klimaschutz und Nachhaltigkeit im Wohnungsbau
74. Use of Speaker Metadata for Improving Automatic Pronunciation Assessment
75. WINVC: One-Shot Voice Conversion with Weight Adaptive Instance Normalization
76. System-independent ASR error detection and classification using Recurrent Neural Network
77. The Effect of Spoken Language on Speech Enhancement Using Self-Supervised Speech Representation Loss Functions
78. Adapting Pretrained Models for Adult to Child Voice Conversion
79. Probing Statistical Representations for End-to-End ASR
80. On Data Sampling Strategies for Training Neural Network Speech Separation Models
81. The University of Sheffield CHiME-7 UDASE Challenge Speech Enhancement System
82. Domain Adaptive Self-supervised Training of Automatic Speech Recognition
83. Learning Cross-lingual Mappings for Data Augmentation to Improve Low-Resource Speech Recognition
84. Exploring Speech Representations for Proficiency Assessment in Language Learning
85. Lightly supervised alignment of subtitles on multi-genre broadcasts
86. Unsupervised crosslingual adaptation of tokenisers for spoken language recognition
87. Perceive and Predict: Self-Supervised Speech Representation Based Loss Functions for Speech Enhancement
88. Towards Domain Generalisation in ASR with Elitist Sampling and Ensemble Knowledge Distillation
89. Deformable Temporal Convolutional Networks for Monaural Noisy Reverberant Speech Separation
90. Acoustic adaptation to dynamic background conditions with asynchronous transformations
91. Hidden model sequence models for automatic speech recognition
92. Long-Term Statistical Feature Extraction from Speech Signal and Its Application in Emotion Recognition
93. Capitalising on North American speech resources for the development of a South African English large vocabulary speech recognition system
94. Non-Linear Pairwise Language Mappings for Low-Resource Multilingual Acoustic Model Fusion
95. Investigating the Impact of Crosslingual Acoustic-Phonetic Similarities on Multilingual Speech Recognition
96. Non-intrusive Speech Intelligibility Metric Prediction for Hearing Impaired Individuals
97. Utterance Weighted Multi-Dilation Temporal Convolutional Networks for Monaural Speech Dereverberation
98. Receptive Field Analysis of Temporal Convolutional Networks for Monaural Speech Dereverberation
99. MetricGAN+/-: Increasing Robustness of Noise Reduction on Unseen Data
100. The 2007 AMI(DA) System for Meeting Transcription
Catalog
Books, media, physical & digital resources
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.