English
Related papers

Related papers: Stateful Conformer with Cache-based Inference for …

200 papers

While Connectionist Temporal Classification (CTC) models deliver state-of-the-art accuracy in automated speech recognition (ASR) pipelines, their performance has been limited by CPU-based beam search decoding. We introduce a GPU-accelerated…

Audio and Speech Processing · Electrical Eng. & Systems 2023-11-10 Daniel Galvez , Tim Kaldewey

Due to the highly parallelizable architecture, Transformer is faster to train than RNN-based models and popularly used in machine translation tasks. However, at inference time, each output word requires all the hidden states of the…

Computation and Language · Computer Science 2019-09-06 Chengyi Wang , Shuangzhi Wu , Shujie Liu

Diffusion models are instrumental in text-to-audio (TTA) generation. Unfortunately, they suffer from slow inference due to an excessive number of queries to the underlying denoising network per generation. To address this bottleneck, we…

Sound · Computer Science 2024-06-25 Yatong Bai , Trung Dang , Dung Tran , Kazuhito Koishida , Somayeh Sojoudi

Streaming processing of speech audio is required for many contemporary practical speech recognition tasks. Even with the large corpora of manually transcribed speech data available today, it is impossible for such corpora to cover…

Computation and Language · Computer Science 2021-04-12 Rodrigo Cabrera , Xiaofeng Liu , Mohammadreza Ghodsi , Zebulun Matteson , Eugene Weinstein , Anjuli Kannan

The Conformer has become the most popular encoder model for automatic speech recognition (ASR). It adds convolution modules to a transformer to learn both local and global dependencies. In this work we describe a faster, more…

Audio and Speech Processing · Electrical Eng. & Systems 2024-04-11 Zengwei Yao , Liyong Guo , Xiaoyu Yang , Wei Kang , Fangjun Kuang , Yifan Yang , Zengrui Jin , Long Lin , Daniel Povey

End-to-end multilingual speech recognition models handle multiple languages through a single model, often incorporating language identification to automatically detect the language of incoming speech. Since the common scenario is where the…

Sound · Computer Science 2024-06-19 Yosuke Kashiwagi , Hayato Futami , Emiru Tsunoo , Siddhant Arora , Shinji Watanabe

Although Transformers have gained success in several speech processing tasks like spoken language understanding (SLU) and speech translation (ST), achieving online processing while keeping competitive performance is still essential for…

Computation and Language · Computer Science 2022-04-20 Keqi Deng , Shinji Watanabe , Jiatong Shi , Siddhant Arora

Automatic speech recognition systems have been largely improved in the past few decades and current systems are mainly hybrid-based and end-to-end-based. The recently proposed CTC-CRF framework inherits the data-efficiency of the hybrid…

Audio and Speech Processing · Electrical Eng. & Systems 2021-07-09 Huahuan Zheng , Wenjie Peng , Zhijian Ou , Jinsong Zhang

The growing need for instant spoken language transcription and translation is driven by increased global communication and cross-lingual interactions. This has made offering translations in multiple languages essential for user…

Computation and Language · Computer Science 2023-10-24 Sara Papi , Peidong Wang , Junkun Chen , Jian Xue , Naoyuki Kanda , Jinyu Li , Yashesh Gaur

This paper introduces a novel Token-and-Duration Transducer (TDT) architecture for sequence-to-sequence tasks. TDT extends conventional RNN-Transducer architectures by jointly predicting both a token and its duration, i.e. the number of…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-31 Hainan Xu , Fei Jia , Somshubra Majumdar , He Huang , Shinji Watanabe , Boris Ginsburg

Recent advances in AudioLLMs have enabled spoken dialogue systems to move beyond turn-based interaction toward real-time full-duplex communication, where the agent must decide when to speak, yield, or interrupt while the user is still…

Transducer and Attention based Encoder-Decoder (AED) are two widely used frameworks for speech-to-text tasks. They are designed for different purposes and each has its own benefits and drawbacks for speech-to-text tasks. In order to…

Computation and Language · Computer Science 2023-05-08 Yun Tang , Anna Y. Sun , Hirofumi Inaguma , Xinyue Chen , Ning Dong , Xutai Ma , Paden D. Tomasello , Juan Pino

End-to-end multi-talker speech recognition is an emerging research trend in the speech community due to its vast potential in applications such as conversation and meeting transcriptions. To the best of our knowledge, all existing research…

Sound · Computer Science 2021-05-12 Liang Lu , Naoyuki Kanda , Jinyu Li , Yifan Gong

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

Although diffusion-based, non-autoregressive text-to-speech (TTS) systems have demonstrated impressive zero-shot synthesis capabilities, their efficacy is still hindered by two key challenges: the difficulty of text-speech alignment…

Audio and Speech Processing · Electrical Eng. & Systems 2026-02-06 Chunyat Wu , Jiajun Deng , Zhengxi Liu , Zheqi Dai , Haolin He , Qiuqiang Kong

Attention-based recurrent neural encoder-decoder models present an elegant solution to the automatic speech recognition problem. This approach folds the acoustic model, pronunciation model, and language model into a single network and…

Audio and Speech Processing · Electrical Eng. & Systems 2018-11-08 Shubham Toshniwal , Anjuli Kannan , Chung-Cheng Chiu , Yonghui Wu , Tara N Sainath , Karen Livescu

This paper presents a class of new fast non-trainable entropy-based confidence estimation methods for automatic speech recognition. We show how per-frame entropy values can be normalized and aggregated to obtain a confidence measure per…

Audio and Speech Processing · Electrical Eng. & Systems 2023-02-09 Aleksandr Laptev , Boris Ginsburg

Having a sequence-to-sequence model which can operate in an online fashion is important for streaming applications such as Voice Search. Neural transducer is a streaming sequence-to-sequence model, but has shown a significant degradation in…

Computation and Language · Computer Science 2017-12-06 Tara N. Sainath , Chung-Cheng Chiu , Rohit Prabhavalkar , Anjuli Kannan , Yonghui Wu , Patrick Nguyen , Zhifeng Chen

This work describes an encoder pre-training procedure using frame-wise label to improve the training of streaming recurrent neural network transducer (RNN-T) model. Streaming RNN-T trained from scratch usually performs worse than…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-14 Lu Huang , Jingyu Sun , Yufeng Tang , Junfeng Hou , Jinkun Chen , Jun Zhang , Zejun Ma

In multi-talker scenarios such as meetings and conversations, speech processing systems are usually required to transcribe the audio as well as identify the speakers for downstream applications. Since overlapped speech is common in this…

Sound · Computer Science 2021-04-07 Liang Lu , Naoyuki Kanda , Jinyu Li , Yifan Gong