English
Related papers

Related papers: Streaming parallel transducer beam search with fas…

200 papers

In the cascaded approach to spoken language translation (SLT), the ASR output is typically punctuated and segmented into sentences before being passed to MT, since the latter is typically trained on written text. However, erroneous…

Computation and Language · Computer Science 2022-10-19 Sukanta Sen , Ondřej Bojar , Barry Haddow

End-to-end automatic speech recognition (ASR) models with a single neural network have recently demonstrated state-of-the-art results compared to conventional hybrid speech recognizers. Specifically, recurrent neural network transducer…

Computation and Language · Computer Science 2020-11-10 Chunxi Liu , Frank Zhang , Duc Le , Suyoun Kim , Yatharth Saraf , Geoffrey Zweig

This paper introduces a highly efficient greedy decoding algorithm for Transducer-based speech recognition models. We redesign the standard nested-loop design for RNN-T decoding, swapping loops over frames and labels: the outer loop…

Audio and Speech Processing · Electrical Eng. & Systems 2025-01-20 Vladimir Bataev , Hainan Xu , Daniel Galvez , Vitaly Lavrukhin , Boris Ginsburg

While large language models (LLMs) have been applied to automatic speech recognition (ASR), the task of making the model streamable remains a challenge. This paper proposes a novel model architecture, Transducer-Llama, that integrates LLMs…

Computation and Language · Computer Science 2024-12-24 Keqi Deng , Jinxi Guo , Yingyi Ma , Niko Moritz , Philip C. Woodland , Ozlem Kalinli , Mike Seltzer

End-to-end model, especially Recurrent Neural Network Transducer (RNN-T), has achieved great success in speech recognition. However, transducer requires a great memory footprint and computing time when processing a long decoding sequence.…

Sound · Computer Science 2023-07-18 Xiaohui Zhang , Mangui Liang , Zhengkun Tian , Jiangyan Yi , Jianhua Tao

Neural transducers have achieved human level performance on standard speech recognition benchmarks. However, their performance significantly degrades in the presence of cross-talk, especially when the primary speaker has a low…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-31 Desh Raj , Junteng Jia , Jay Mahadeokar , Chunyang Wu , Niko Moritz , Xiaohui Zhang , Ozlem Kalinli

Conformer models maintain a large number of internal states, the vast majority of which are associated with self-attention layers. With limited memory bandwidth, reading these from memory at each inference step can slow down inference. In…

Computation and Language · Computer Science 2023-04-04 Rami Botros , Anmol Gulati , Tara N. Sainath , Krzysztof Choromanski , Ruoming Pang , Trevor Strohman , Weiran Wang , Jiahui Yu

The Streaming Unmixing and Recognition Transducer (SURT) model was proposed recently as an end-to-end approach for continuous, streaming, multi-talker speech recognition (ASR). Despite impressive results on multi-turn meetings, SURT has…

Audio and Speech Processing · Electrical Eng. & Systems 2023-09-20 Desh Raj , Daniel Povey , Sanjeev Khudanpur

We propose an efficient batching strategy for variable-length decoding on GPU architectures. During decoding, when candidates terminate or are pruned according to heuristics, our streaming approach periodically "refills" the batch before…

Computation and Language · Computer Science 2021-08-17 Kevin Yang , Violet Yao , John DeNero , Dan Klein

Streaming recognition and segmentation of multi-party conversations with overlapping speech is crucial for the next generation of voice assistant applications. In this work we address its challenges discovered in the previous work on…

Audio and Speech Processing · Electrical Eng. & Systems 2022-05-12 Ilya Sklyar , Anna Piunova , Christian Osendorfer

This paper proposes a novel non-autoregressive (NAR) block-based Attention Mask Decoder (AMD) that flexibly balances performance-efficiency trade-offs for Conformer ASR systems. AMD performs parallel NAR inference within contiguous blocks…

While speech recognition Word Error Rate (WER) has reached human parity for English, long-form dictation scenarios still suffer from segmentation and punctuation problems resulting from irregular pausing patterns or slow speakers.…

Computation and Language · Computer Science 2022-12-07 Piyush Behre , Sharman Tan , Padma Varadharajan , Shuangyu Chang

Transformers have become a predominant machine learning workload, they are not only the de-facto standard for natural language processing tasks, but they are also being deployed in other domains such as vision and speech recognition. Many…

Machine Learning · Computer Science 2022-06-23 Ibrahim Ahmed , Sahil Parmar , Matthew Boyd , Michael Beidler , Kris Kang , Bill Liu , Kyle Roach , John Kim , Dennis Abts

Recently, there has been an increasing interest in two-pass streaming end-to-end speech recognition (ASR) that incorporates a 2nd-pass rescoring model on top of the conventional 1st-pass streaming ASR model to improve recognition accuracy…

Computation and Language · Computer Science 2022-11-17 Suyoun Kim , Ke Li , Lucas Kabela , Rongqing Huang , Jiedan Zhu , Ozlem Kalinli , Duc Le

Deep biasing for the Transducer can improve the recognition performance of rare words or contextual entities, which is essential in practical applications, especially for streaming Automatic Speech Recognition (ASR). However, deep biasing…

Computation and Language · Computer Science 2023-11-16 Jin Qiu , Lu Huang , Boyu Li , Jun Zhang , Lu Lu , Zejun Ma

Streaming voice conversion has become increasingly popular for its potential in real-time applications. The recently proposed DualVC 2 has achieved robust and high-quality streaming voice conversion with a latency of about 180ms.…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-13 Ziqian Ning , Shuai Wang , Pengcheng Zhu , Zhichao Wang , Jixun Yao , Lei Xie , Mengxiao Bi

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

The RNN-Transducer (RNN-T) framework for speech recognition has been growing in popularity, particularly for deployed real-time ASR systems, because it combines high accuracy with naturally streaming recognition. One of the drawbacks of…

Audio and Speech Processing · Electrical Eng. & Systems 2022-06-28 Fangjun Kuang , Liyong Guo , Wei Kang , Long Lin , Mingshuang Luo , Zengwei Yao , Daniel Povey

Recently, Transformer based end-to-end models have achieved great success in many areas including speech recognition. However, compared to LSTM models, the heavy computational cost of the Transformer during inference is a key issue to…

Computation and Language · Computer Science 2021-03-02 Xie Chen , Yu Wu , Zhenghao Wang , Shujie Liu , Jinyu Li

We design an online end-to-end speech recognition system based on Time-Depth Separable (TDS) convolutions and Connectionist Temporal Classification (CTC). We improve the core TDS architecture in order to limit the future context and hence…