English
Related papers

Related papers: E2E Segmenter: Joint Segmenting and Decoding for L…

200 papers

Speaker segmentation consists in partitioning a conversation between one or more speakers into speaker turns. Usually addressed as the late combination of three sub-tasks (voice activity detection, speaker change detection, and overlapped…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-11 Hervé Bredin , Antoine Laurent

Speech segmentation, which splits long speech into short segments, is essential for speech translation (ST). Popular VAD tools like WebRTC VAD have generally relied on pause-based segmentation. Unfortunately, pauses in speech do not…

Computation and Language · Computer Science 2022-07-14 Ryo Fukuda , Katsuhito Sudoh , Satoshi Nakamura

Voice activity detection (VAD) is an essential pre-processing step for tasks such as automatic speech recognition (ASR) and speaker recognition. A basic goal is to remove silent segments within an audio, while a more general VAD system…

Audio and Speech Processing · Electrical Eng. & Systems 2020-09-22 Yefei Chen , Shuai Wang , Yanmin Qian , Kai Yu

State-of-the-art end-to-end automatic speech recognition (ASR) extracts acoustic features from input speech signal every 10 ms which corresponds to a frame rate of 100 frames/second. In this report, we investigate the use of high-frame-rate…

Audio and Speech Processing · Electrical Eng. & Systems 2019-07-15 Cong-Thanh Do

ASR endpointing (EP) plays a major role in delivering a good user experience in products supporting human or artificial agents in human-human/machine conversations. Transducer-based ASR (T-ASR) is an end-to-end (E2E) ASR modelling technique…

Past studies on end-to-end meeting transcription have focused on model architecture and have mostly been evaluated on simulated meeting data. We present a novel study aiming to optimize the use of a Speaker-Attributed ASR (SA-ASR) system in…

Computation and Language · Computer Science 2024-09-06 Can Cui , Imran Ahamad Sheikh , Mostafa Sadeghi , Emmanuel Vincent

While speech recognition Word Error Rate (WER) has reached human parity for English, continuous speech recognition scenarios such as voice typing and meeting transcriptions still suffer from segmentation and punctuation problems, resulting…

Computation and Language · Computer Science 2023-01-11 Piyush Behre , Sharman Tan , Padma Varadharajan , Shuangyu Chang

End-to-end (E2E) automatic speech recognition (ASR) models, by now, have shown competitive performance on several benchmarks. These models are structured to either operate in streaming or non-streaming mode. This work presents cascaded…

Audio and Speech Processing · Electrical Eng. & Systems 2020-10-29 Arun Narayanan , Tara N. Sainath , Ruoming Pang , Jiahui Yu , Chung-Cheng Chiu , Rohit Prabhavalkar , Ehsan Variani , Trevor Strohman

The demand for fast and accurate incremental speech recognition increases as the applications of automatic speech recognition (ASR) proliferate. Incremental speech recognizers output chunks of partially recognized words while the user is…

Computation and Language · Computer Science 2020-08-18 Yuan Shangguan , Kate Knister , Yanzhang He , Ian McGraw , Francoise Beaufays

Transformer-based end-to-end (E2E) automatic speech recognition (ASR) systems have recently gained wide popularity, and are shown to outperform E2E models based on recurrent structures on a number of ASR tasks. However, like other E2E…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-30 Mohan Li , Catalin Zorila , Rama Doddipatla

End-to-end modeling (E2E) of automatic speech recognition (ASR) blends all the components of a traditional speech recognition system into a unified model. Although it simplifies training and decoding pipelines, the unified model is hard to…

Computation and Language · Computer Science 2018-12-06 Zhehuai Chen , Mahaveer Jain , Yongqiang Wang , Michael L. Seltzer , Christian Fuegen

Automatic speech recognition (ASR) systems are primarily evaluated on transcription accuracy. However, in some use cases such as subtitling, verbatim transcription would reduce output readability given limited screen size and reading time.…

Computation and Language · Computer Science 2020-05-26 Danni Liu , Jan Niehues , Gerasimos Spanakis

Despite recent advances in voice separation methods, many challenges remain in realistic scenarios such as noisy recording and the limits of available data. In this work, we propose to explicitly incorporate the phonetic and linguistic…

The vast majority of ASR research uses corpora in which both the training and test data have been pre-segmented into utterances. In most real-word ASR use-cases, however, test audio is not segmented, leading to a mismatch between…

Computation and Language · Computer Science 2023-09-27 Jennifer Drexler Fox , Desh Raj , Natalie Delworth , Quinn McNamara , Corey Miller , Migüel Jetté

The vector representations of fixed dimensionality for words (in text) offered by Word2Vec have been shown to be very useful in many application scenarios, in particular due to the semantic information they carry. This paper proposes a…

Sound · Computer Science 2016-06-14 Yu-An Chung , Chao-Chung Wu , Chia-Hao Shen , Hung-Yi Lee , Lin-Shan Lee

The audio segmentation mismatch between training data and those seen at run-time is a major problem in direct speech translation. Indeed, while systems are usually trained on manually segmented corpora, in real use cases they are often…

Sound · Computer Science 2021-10-15 Marco Gaido , Matteo Negri , Mauro Cettolo , Marco Turchi

End-to-end (E2E) automatic speech recognition (ASR) systems directly map acoustics to words using a unified model. Previous works mostly focus on E2E training a single model which integrates acoustic and language model into a whole.…

Computation and Language · Computer Science 2018-03-06 Zhehuai Chen , Qi Liu , Hao Li , Kai Yu

Non-autoregressive (NAR) modeling has gained more and more attention in speech processing. With recent state-of-the-art attention-based automatic speech recognition (ASR) structure, NAR can realize promising real-time factor (RTF)…

Audio and Speech Processing · Electrical Eng. & Systems 2021-07-21 Tianzi Wang , Yuya Fujita , Xuankai Chang , Shinji Watanabe

Speech activity detection (SAD) plays an important role in current speech processing systems, including automatic speech recognition (ASR). SAD is particularly difficult in environments with acoustic noise. A practical solution is to…

Computation and Language · Computer Science 2023-05-15 Fei Tao , Carlos Busso

One challenge in speech translation is that plenty of spoken content is long-form, but short units are necessary for obtaining high-quality translations. To address this mismatch, we adapt large language models (LLMs) to split long ASR…

Computation and Language · Computer Science 2023-10-24 Arya D. McCarthy , Hao Zhang , Shankar Kumar , Felix Stahlberg , Ke Wu