English
Related papers

Related papers: Zipformer: A faster and better encoder for automat…

200 papers

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

We introduce dual-decoder Transformer, a new model architecture that jointly performs automatic speech recognition (ASR) and multilingual speech translation (ST). Our models are based on the original Transformer architecture (Vaswani et…

Computation and Language · Computer Science 2020-11-21 Hang Le , Juan Pino , Changhan Wang , Jiatao Gu , Didier Schwab , Laurent Besacier

Recently, Transformer-based architectures have been explored for speaker embedding extraction. Although the Transformer employs the self-attention mechanism to efficiently model the global interaction between token embeddings, it is…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-02 Mufan Sang , Yong Zhao , Gang Liu , John H. L. Hansen , Jian Wu

Optimization of modern ASR architectures is among the highest priority tasks since it saves many computational resources for model training and inference. The work proposes a new Uconv-Conformer architecture based on the standard Conformer…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-14 Andrei Andrusenko , Rauf Nasretdinov , Aleksei Romanenko

Self-supervised learned (SSL) models such as Wav2vec and HuBERT yield state-of-the-art results on speech-related tasks. Given the effectiveness of such models, it is advantageous to use them in conventional ASR systems. While some…

Computation and Language · Computer Science 2024-04-22 Darshan Prabhu , Sai Ganesh Mirishkar , Pankaj Wasnik

The streaming automatic speech recognition (ASR) models are more popular and suitable for voice-based applications. However, non-streaming models provide better performance as they look at the entire audio context. To leverage the benefits…

Sound · Computer Science 2022-08-26 Raviraj Joshi , Subodh Kumar

Transformers have recently achieved state-of-the-art performance in speech separation. These models, however, are computationally demanding and require a lot of learnable parameters. This paper explores Transformer-based speech separation…

Audio and Speech Processing · Electrical Eng. & Systems 2024-01-17 Luca Della Libera , Cem Subakan , Mirco Ravanelli , Samuele Cornell , Frédéric Lepoutre , François Grondin

Recently, Transformer-based encoder-decoder models have demonstrated strong performance in multilingual speech recognition. However, the decoder's autoregressive nature and large size introduce significant bottlenecks during inference.…

Audio and Speech Processing · Electrical Eng. & Systems 2025-08-28 Yunkyu Lim , Jihwan Park , Hyung Yong Kim , Hanbin Lee , Byeong-Yeol Kim

Conformer has achieved impressive results in Automatic Speech Recognition (ASR) by leveraging transformer's capturing of content-based global interactions and convolutional neural network's exploiting of local features. In Conformer, two…

Computation and Language · Computer Science 2022-09-02 Xianchao Wu

Convolutional neural networks (CNN) have improved speech recognition performance greatly by exploiting localized time-frequency patterns. But these patterns are assumed to appear in symmetric and rigid kernels by the conventional CNN…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-19 Jiamin Xie , John H. L. Hansen

Recently, transformer-based models have demonstrated remarkable performance on audio-visual segmentation (AVS) tasks. However, their expensive computational cost makes real-time inference impractical. By characterizing attention maps of the…

Computer Vision and Pattern Recognition · Computer Science 2024-08-06 Zili Wang , Qi Yang , Linsu Shi , Jiazhong Yu , Qinghua Liang , Fei Li , Shiming Xiang

This paper proposes a simple yet effective way of regularising the encoder-decoder-based automatic speech recognition (ASR) models that enhance the robustness of the model and improve the generalisation to out-of-domain scenarios. The…

Audio and Speech Processing · Electrical Eng. & Systems 2024-10-24 Alexander Polok , Santosh Kesiraju , Karel Beneš , Lukáš Burget , Jan Černocký

Automatic Speech Recognition (ASR) has seen remarkable progress, with models like OpenAI Whisper and NVIDIA Canary achieving state-of-the-art (SOTA) performance in offline transcription. However, these models are not designed for streaming…

Computation and Language · Computer Science 2026-04-07 Tomer Krichli , Bhiksha Raj , Joseph Keshet

Automatic speech recognition (ASR) has reached a level of accuracy in recent years, that even outperforms humans in transcribing speech to text. Nevertheless, all current ASR approaches show a certain weakness against ambient noise. To…

Sound · Computer Science 2023-12-22 Christopher Simic , Tobias Bocklet

We study speech intent classification and slot filling (SICSF) by proposing to use an encoder pretrained on speech recognition (ASR) to initialize an end-to-end (E2E) Conformer-Transformer model, which achieves the new state-of-the-art…

Computation and Language · Computer Science 2023-07-17 He Huang , Jagadeesh Balam , Boris Ginsburg

Current ASR systems are mainly trained and evaluated at the utterance level. Long range cross utterance context can be incorporated. A key task is to derive a suitable compact representation of the most relevant history contexts. In…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-27 Mingyu Cui , Jiawen Kang , Jiajun Deng , Xi Yin , Yutao Xie , Xie Chen , Xunying Liu

In this paper, we propose an efficient and accurate streaming speech recognition model based on the FastConformer architecture. We adapted the FastConformer architecture for streaming applications through: (1) constraining both the…

Computation and Language · Computer Science 2024-05-06 Vahid Noroozi , Somshubra Majumdar , Ankur Kumar , Jagadeesh Balam , Boris Ginsburg

We propose automatic speech recognition (ASR) models inspired by echo state network (ESN), in which a subset of recurrent neural networks (RNN) layers in the models are randomly initialized and untrained. Our study focuses on RNN-T and…

Computation and Language · Computer Science 2021-02-19 Harsh Shrivastava , Ankush Garg , Yuan Cao , Yu Zhang , Tara Sainath

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

End-to-end models are fast replacing the conventional hybrid models in automatic speech recognition. Transformer, a sequence-to-sequence model, based on self-attention popularly used in machine translation tasks, has given promising results…

Audio and Speech Processing · Electrical Eng. & Systems 2021-11-19 Vishwas M. Shetty , Metilda Sagaya Mary N J , S. Umesh