English
Related papers

Related papers: Incremental Transfer Learning in Two-pass Informat…

200 papers

End-to-end speaker diarization enables accurate overlap-aware diarization by jointly estimating multiple speakers' speech activities in parallel. This approach is data-hungry, requiring a large amount of labeled conversational data, which…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-02 Shota Horiguchi , Atsushi Ando , Marc Delcroix , Naohiro Tawara

Information bottleneck is an information-theoretic principle of representation learning that aims to learn a maximally compressed representation that preserves as much information about labels as possible. Under this principle, two…

Information Theory · Computer Science 2023-11-08 Yuyan Ni , Yanyan Lan , Ao Liu , Zhiming Ma

The current paradigm of large-scale pre-training and fine-tuning Transformer large language models has lead to significant improvements across the board in natural language processing. However, such large models are susceptible to…

Machine Learning · Computer Science 2023-12-04 Fabio Fehr , James Henderson

Compensation for channel mismatch and noise interference is essential for robust automatic speech recognition. Enhanced speech has been introduced into the multi-condition training of acoustic models to improve their generalization ability.…

Sound · Computer Science 2022-11-24 Hung-Shin Lee , Pin-Yuan Chen , Yao-Fei Cheng , Yu Tsao , Hsin-Min Wang

Task-oriented communication aims to extract and transmit task-relevant information to significantly reduce the communication overhead and transmission latency. However, the unpredictable distribution shifts between training and test data,…

Signal Processing · Electrical Eng. & Systems 2024-05-16 Hongru Li , Jiawei Shao , Hengtao He , Shenghui Song , Jun Zhang , Khaled B. Letaief

In the task of speaker diarization, the number of small-scale meetings accounts for a large proportion. When microphone arrays are employed as a recording device, its spatial information is usually ignored by most researchers. In this…

Sound · Computer Science 2022-10-27 Yuxuan Du , Ruohua Zhou

While the use of deep neural networks has significantly boosted speaker recognition performance, it is still challenging to separate speakers in poor acoustic environments. To improve robustness of speaker recognition system performance in…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-19 Yanpei Shi , Qiang Huang , Thomas Hain

Recently, end-to-end automatic speech recognition models based on connectionist temporal classification (CTC) have achieved impressive results, especially when fine-tuned from wav2vec2.0 models. Due to the conditional independence…

Computation and Language · Computer Science 2022-03-08 Keqi Deng , Songjun Cao , Yike Zhang , Long Ma , Gaofeng Cheng , Ji Xu , Pengyuan Zhang

When the available data of a target speaker is insufficient to train a high quality speaker-dependent neural text-to-speech (TTS) system, we can combine data from multiple speakers and train a multi-speaker TTS model instead. Many studies…

Audio and Speech Processing · Electrical Eng. & Systems 2019-04-09 Hieu-Thi Luong , Xin Wang , Junichi Yamagishi , Nobuyuki Nishizawa

Inverse text normalization (ITN) is crucial for converting spoken-form into written-form, especially in the context of automatic speech recognition (ASR). While most downstream tasks of ASR rely on written-form, ASR systems often output…

Computation and Language · Computer Science 2023-09-19 Juntae Kim , Minkyu Lim , Seokjin Hong

Spoken language diarization (LD) and related tasks are mostly explored using the phonotactic approach. Phonotactic approaches mostly use explicit way of language modeling, hence requiring intermediate phoneme modeling and transcribed data.…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-23 Jagabandhu Mishra , Amartya Chowdhury , S. R. Mahadeva Prasanna

It has been shown that the intelligibility of noisy speech can be improved by speech enhancement algorithms. However, speech enhancement has not been established as an effective frontend for robust automatic speech recognition (ASR) in…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-22 Yufeng Yang , Ashutosh Pandey , DeLiang Wang

State-of-the-art deep learning systems rely on iterative distributed training to tackle the increasing complexity of models and input data. The iteration time in these communication-heavy systems depends on the computation time,…

Distributed, Parallel, and Cluster Computing · Computer Science 2018-10-05 Sayed Hadi Hashemi , Sangeetha Abdu Jyothi , Roy H. Campbell

Building ASR systems robust to foreign-accented speech is an important challenge in today's globalized world. A prior study explored the way to enhance the performance of phonetic token-based ASR on accented speech by reproducing the…

Sound · Computer Science 2026-01-28 Kentaro Onda , Satoru Fukayama , Daisuke Saito , Nobuaki Minematsu

The scarcity of labeled audio-visual datasets is a constraint for training superior audio-visual speaker diarization systems. To improve the performance of audio-visual speaker diarization, we leverage pre-trained supervised and…

Audio and Speech Processing · Electrical Eng. & Systems 2023-12-08 Huan Zhao , Li Zhang , Yue Li , Yannan Wang , Hongji Wang , Wei Rao , Qing Wang , Lei Xie

Automatic speaker verification (ASV) systems, which determine whether two speeches are from the same speaker, mainly focus on verification accuracy while ignoring inference speed. However, in real applications, both inference speed and…

Sound · Computer Science 2022-04-05 Ruiteng Zhang , Jianguo Wei , Wenhuan Lu , Lin Zhang , Yantao Ji , Junhai Xu , Xugang Lu

Speaker Diarization is the problem of separating speakers in an audio. There could be any number of speakers and final result should state when speaker starts and ends. In this project, we analyze given audio file with 2 channels and 2…

Audio and Speech Processing · Electrical Eng. & Systems 2020-06-11 Vishal Sharma , Zekun Zhang , Zachary Neubert , Curtis Dyreson

Fine-tuning is a popular method for adapting text-to-speech (TTS) models to new speakers. However this approach has some challenges. Usually fine-tuning requires several hours of high quality speech per speaker. There is also that…

Audio and Speech Processing · Electrical Eng. & Systems 2022-11-02 Cheng-Ping Hsieh , Subhankar Ghosh , Boris Ginsburg

Simultaneous Speech Translation (SimulST) requires balancing high translation quality with low latency. Recent work introduced REINA, a method that trains a Read/Write policy based on estimating the information gain of reading more audio.…

Machine Learning · Computer Science 2026-04-14 Joseph Liu , Nameer Hirschkind , Xiao Yu , Mahesh Kumar Nandwana

In this paper, we investigate the semi-supervised joint training of text to speech (TTS) and automatic speech recognition (ASR), where a small amount of paired data and a large amount of unpaired text data are available. Conventional…

Sound · Computer Science 2022-07-12 Naoki Makishima , Satoshi Suzuki , Atsushi Ando , Ryo Masumura