English
Related papers

Related papers: Pushing the Limits of Beam Search Decoding for Tra…

200 papers

A streaming style inference of encoder-decoder automatic speech recognition (ASR) system is important for reducing latency, which is essential for interactive use cases. To this end, we propose a novel blockwise synchronous decoding…

Audio and Speech Processing · Electrical Eng. & Systems 2022-01-26 Emiru Tsunoo , Chaitanya Narisetty , Michael Hentschel , Yosuke Kashiwagi , Shinji Watanabe

In sequence-to-sequence Transformer ASR, autoregressive (AR) models achieve strong accuracy but suffer from slow decoding, while non-autoregressive (NAR) models enable parallel decoding at the cost of degraded performance. We propose a…

Audio and Speech Processing · Electrical Eng. & Systems 2026-02-26 Hao Yen , Pin-Jui Ku , Ante Jukić , Sabato Marco Siniscalchi

Neural transducers provide a natural way of streaming ASR. However, they augment output sequences with blank tokens which leads to challenges for domain adaptation using text data. This paper proposes a label-synchronous neural transducer…

Audio and Speech Processing · Electrical Eng. & Systems 2023-10-12 Keqi Deng , Philip C. Woodland

We propose a new scalable method to optimize the architecture of an artificial neural network. The proposed algorithm, called Greedy Search for Neural Network Architecture, aims to determine a neural network with minimal number of layers…

Machine Learning · Computer Science 2021-04-30 Massimiliano Lupo Pasini , Junqi Yin , Ying Wai Li , Markus Eisenbach

Transformer has achieved competitive performance against state-of-the-art end-to-end models in automatic speech recognition (ASR), and requires significantly less training time than RNN-based models. The original Transformer, with…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-14 Wenyong Huang , Wenchao Hu , Yu Ting Yeung , Xiao Chen

Neural architecture search (NAS) is an attractive approach to automate the design of optimized architectures but is constrained by high computational budget, especially when optimizing for multiple, important conflicting objectives. To…

Machine Learning · Computer Science 2025-09-03 Zhao Wei , Chin Chun Ooi , Yew-Soon Ong

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

Streaming automatic speech recognition (ASR) aims to emit each hypothesized word as quickly and accurately as possible. However, emitting fast without degrading quality, as measured by word error rate (WER), is highly challenging. Existing…

Audio and Speech Processing · Electrical Eng. & Systems 2021-02-05 Jiahui Yu , Chung-Cheng Chiu , Bo Li , Shuo-yiin Chang , Tara N. Sainath , Yanzhang He , Arun Narayanan , Wei Han , Anmol Gulati , Yonghui Wu , Ruoming Pang

With the increasing demands on future wireless systems, new design objectives become eminent. Low-density parity-check codes together with belief propagation (BP) decoding have outstanding performance for large block lengths. Yet, for…

Information Theory · Computer Science 2024-06-06 Jonathan Mandelbaum , Sisi Miao , Nils Albert Schwendemann , Holger Jäkel , Laurent Schmalen

This paper proposes a unified framework, All-in-One ASR, that allows a single model to support multiple automatic speech recognition (ASR) paradigms, including connectionist temporal classification (CTC), attention-based encoder-decoder…

Audio and Speech Processing · Electrical Eng. & Systems 2025-12-15 Takafumi Moriya , Masato Mimura , Tomohiro Tanaka , Hiroshi Sato , Ryo Masumura , Atsunori Ogawa

The Breadth First Search (BFS) algorithm is the foundation and building block of many higher graph-based operations such as spanning trees, shortest paths and betweenness centrality. The importance of this algorithm increases each day due…

Distributed, Parallel, and Cluster Computing · Computer Science 2017-04-04 Julian Romera

We present an improvement of our implementation of the Correlation Technique for the Fourier Domain Acceleration Search (FDAS) algorithm on Graphics Processor Units (GPUs) (Dimoudi & Armour 2015; Dimoudi et al. 2017). Our new improved…

Instrumentation and Methods for Astrophysics · Physics 2017-11-30 Karel Adámek , Sofia Dimoudi , Mike Giles , Wesley Armour

Beam search, which is the dominant ASR decoding algorithm for end-to-end models, generates tree-structured hypotheses. However, recent studies have shown that decoding with hypothesis merging can achieve a more efficient search with…

Sound · Computer Science 2022-08-04 Jiatong Shi , George Saon , David Haws , Shinji Watanabe , Brian Kingsbury

The vast majority of inference time for RNN Transducer (RNN-T) models today is spent on decoding. Current state-of-the-art RNN-T decoding implementations leave the GPU idle ~80% of the time. Leveraging a new CUDA 12.4 feature, CUDA graph…

Machine Learning · Computer Science 2024-06-07 Daniel Galvez , Vladimir Bataev , Hainan Xu , Tim Kaldewey

We propose Windowed Inference for Non-blank Detection (WIND), a novel strategy that significantly accelerates RNN-T inference without compromising model accuracy. During model inference, instead of processing frames sequentially, WIND…

Machine Learning · Computer Science 2025-05-21 Hainan Xu , Vladimir Bataev , Lilit Grigoryan , Boris Ginsburg

We present AutoMode-ASR, a novel framework that effectively integrates multiple ASR systems to enhance the overall transcription quality while optimizing cost. The idea is to train a decision model to select the optimal ASR system for each…

Computation and Language · Computer Science 2024-09-20 Ahmet Gündüz , Yunsu Kim , Kamer Ali Yuksel , Mohamed Al-Badrashiny , Thiago Castro Ferreira , Hassan Sawaf

The neural transducer is an end-to-end model for automatic speech recognition (ASR). While the model is well-suited for streaming ASR, the training process remains challenging. During training, the memory requirements may quickly exceed the…

Computation and Language · Computer Science 2023-03-14 Stefan Braun , Erik McDermott , Roger Hsiao

Embedding models can generate high-dimensional vectors whose similarity reflects semantic affinities. Thus, accurately and timely retrieving those vectors in a large collection that are similar to a given query has become a critical…

Information Retrieval · Computer Science 2024-10-31 Mariano Tepper , Ishwar Singh Bhati , Cecilia Aguerrebere , Ted Willke

This paper presents a neural architecture search method based on Transformer architecture, searching cross multihead attention computation ways for different number of encoder and decoder combinations. In order to search for neural network…

Computation and Language · Computer Science 2025-11-03 Shang Wang , Huanrong Tang , Jianquan Ouyang

This paper delves into the challenging task of Active Speaker Detection (ASD), where the system needs to determine in real-time whether a person is speaking or not in a series of video frames. While previous works have made significant…

Computer Vision and Pattern Recognition · Computer Science 2024-09-16 Arnav Kundu , Yanzi Jin , Mohammad Sekhavat , Max Horton , Danny Tormoen , Devang Naik