English
Related papers

Related papers: Augmenting conformers with structured state-space …

200 papers

We propose a fully convolutional sequence-to-sequence encoder architecture with a simple and efficient decoder. Our model improves WER on LibriSpeech while being an order of magnitude more efficient than a strong RNN baseline. Key to our…

Computation and Language · Computer Science 2019-04-05 Awni Hannun , Ann Lee , Qiantong Xu , Ronan Collobert

Large-scale language models (LLMs) such as GPT-2, BERT and RoBERTa have been successfully applied to ASR N-best rescoring. However, whether or how they can benefit competitive, near state-of-the-art ASR systems remains unexplored. In this…

Computation and Language · Computer Science 2022-08-19 Takuma Udagawa , Masayuki Suzuki , Gakuto Kurata , Nobuyasu Itoh , George Saon

In this paper, we show that a simple self-supervised pre-trained audio model can achieve comparable inference efficiency to more complicated pre-trained models with speech transformer encoders. These speech transformers rely on mixing…

Sound · Computer Science 2024-02-09 Sungho Jeon , Ching-Feng Yeh , Hakan Inan , Wei-Ning Hsu , Rashi Rungta , Yashar Mehdad , Daniel Bikel

Spoken dialogue systems typically use a list of top-N ASR hypotheses for inferring the semantic meaning and tracking the state of the dialogue. However ASR graphs, such as confusion networks (confnets), provide a compact representation of a…

Computation and Language · Computer Science 2022-04-11 Vaishali Pal , Fabien Guillot , Manish Shrivastava , Jean-Michel Renders , Laurent Besacier

In this study, we delve into the efficacy of transformers within pre-trained language models (PLMs) when repurposed as encoders for Automatic Speech Recognition (ASR). Our underlying hypothesis posits that, despite being initially trained…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-27 Keyu An , Shiliang Zhang , Zhijie Yan

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

This paper investigates four types of cross-utterance speech contexts modeling approaches for streaming and non-streaming Conformer-Transformer (C-T) ASR systems: i) input audio feature concatenation; ii) cross-utterance Encoder embedding…

Audio and Speech Processing · Electrical Eng. & Systems 2025-08-15 Mingyu Cui , Mengzhe Geng , Jiajun Deng , Chengxi Deng , Jiawen Kang , Shujie Hu , Guinan Li , Tianzi Wang , Zhaoqing Li , Xie Chen , Xunying Liu

The recurrent neural network transducer (RNN-T) is a prominent streaming end-to-end (E2E) ASR technology. In RNN-T, the acoustic encoder commonly consists of stacks of LSTMs. Very recently, as an alternative to LSTM layers, the Conformer…

General-purpose automatic speech recognition (ASR) systems do not always perform well in goal-oriented dialogue. Existing ASR correction methods rely on prior user data or named entities. We extend correction to tasks that have no prior…

Computation and Language · Computer Science 2025-01-13 Yuya Asano , Sabit Hassan , Paras Sharma , Anthony Sicilia , Katherine Atwell , Diane Litman , Malihe Alikhani

Improving the performance of end-to-end ASR models on long utterances ranging from minutes to hours in length is an ongoing challenge in speech recognition. A common solution is to segment the audio in advance using a separate voice…

We present a Conformer-based end-to-end neural diarization (EEND) model that uses both acoustic input and features derived from an automatic speech recognition (ASR) model. Two categories of features are explored: features derived directly…

Computation and Language · Computer Science 2022-07-13 Aparna Khare , Eunjung Han , Yuguang Yang , Andreas Stolcke

Sequence-to-sequence models have shown success in end-to-end speech recognition. However these models have only used shallow acoustic encoder networks. In our work, we successively train very deep convolutional networks to add more…

Computation and Language · Computer Science 2016-10-11 Yu Zhang , William Chan , Navdeep Jaitly

In this paper, we investigate domain adaptation for low-resource Automatic Speech Recognition (ASR) of target-domain data, when a well-trained ASR model trained with a large dataset is available. We argue that in the encoder-decoder…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-30 Vrunda N. Sukhadia , S. Umesh

Automatic speech recognition (ASR) with an encoder equipped with self-attention, whether streaming or non-streaming, takes quadratic time in the length of the speech utterance. This slows down training and decoding, increase their cost, and…

Sound · Computer Science 2024-09-12 Titouan Parcollet , Rogier van Dalen , Shucong Zhang , Sourav Batthacharya

Self-supervised automatic speech recognition (SSL-ASR) is an ASR approach that uses speech encoders pretrained on large amounts of unlabeled audio (e.g., wav2vec2.0 or HuBERT) and then fine-tunes them with limited labeled data to perform…

Audio and Speech Processing · Electrical Eng. & Systems 2026-01-07 Eyal Cohen , Bhiksha Raj , Joseph Keshet

SLU combines ASR and NLU capabilities to accomplish speech-to-intent understanding. In this paper, we compare different ways to combine ASR and NLU, in particular using a single Conformer model with different ways to use its components, to…

Computation and Language · Computer Science 2022-04-11 Nick J. C. Wang , Shaojun Wang , Jing Xiao

This paper presents an overview and evaluation of some of the end-to-end ASR models on long-form audios. We study three categories of Automatic Speech Recognition(ASR) models based on their core architecture: (1) convolutional, (2)…

Audio and Speech Processing · Electrical Eng. & Systems 2023-09-22 Nithin Rao Koluguri , Samuel Kriman , Georgy Zelenfroind , Somshubra Majumdar , Dima Rekesh , Vahid Noroozi , Jagadeesh Balam , Boris Ginsburg

This paper studies a novel pre-training technique with unpaired speech data, Speech2C, for encoder-decoder based automatic speech recognition (ASR). Within a multi-task learning framework, we introduce two pre-training tasks for the…

Sound · Computer Science 2022-06-22 Junyi Ao , Ziqiang Zhang , Long Zhou , Shujie Liu , Haizhou Li , Tom Ko , Lirong Dai , Jinyu Li , Yao Qian , Furu Wei

Recently, a few novel streaming attention-based sequence-to-sequence (S2S) models have been proposed to perform online speech recognition with linear-time decoding complexity. However, in these models, the decisions to generate tokens are…

Computation and Language · Computer Science 2020-05-18 Hirofumi Inaguma , Yashesh Gaur , Liang Lu , Jinyu Li , Yifan Gong

This paper presents Seewo's systems for both tracks of the Multilingual Conversational Speech Language Model Challenge (MLC-SLM), addressing automatic speech recognition (ASR) and speaker diarization with ASR (SD-ASR). We introduce a…

Computation and Language · Computer Science 2025-06-19 Bo Li , Chengben Xu , Wufeng Zhang