English
Related papers

Related papers: LAE: Language-Aware Encoder for Monolingual and Mu…

200 papers

State-of-the-art Variational Auto-Encoders (VAEs) for learning disentangled latent representations give impressive results in discovering features like pitch, pause duration, and accent in speech data, leading to highly controllable…

Sound · Computer Science 2021-05-11 Shakti Kumar , Jithin Pradeep , Hussain Zaidi

This paper presents our latest investigation on end-to-end automatic speech recognition (ASR) for overlapped speech. We propose to train an end-to-end system conditioned on speaker embeddings and further improved by transfer learning from…

Audio and Speech Processing · Electrical Eng. & Systems 2019-08-14 Pavel Denisov , Ngoc Thang Vu

Representation learning (RL) methods for cyberattack detection face the diversity and sophistication of attack data, leading to the issue of mixed representations of different classes, particularly as the number of classes increases. To…

Cryptography and Security · Computer Science 2025-04-30 Phai Vu Dinh , Quang Uy Nguyen , Thai Hoang Dinh , Diep N. Nguyen , Bao Son Pham , Eryk Dutkiewicz

The lack of code-switch training data is one of the major concerns in the development of end-to-end code-switching automatic speech recognition (ASR) models. In this work, we propose a method to train an improved end-to-end code-switching…

Computation and Language · Computer Science 2021-01-14 Yerbolat Khassanov , Haihua Xu , Van Tung Pham , Zhiping Zeng , Eng Siong Chng , Chongjia Ni , Bin Ma

Decoding continuous speech from intracortical recordings is a central challenge for brain-computer interfaces (BCIs), with transformative potential for individuals with conditions that impair their ability to speak. While recent…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-17 Tommaso Boccato , Michal Olak , Matteo Ferrante

Although the deep integration of the Automatic Speech Recognition (ASR) system with Large Language Models (LLMs) has significantly improved accuracy, the deployment of such systems in low-latency streaming scenarios remains challenging. In…

Sound · Computer Science 2026-03-13 Yinfeng Xia , Jian Tang , Junfeng Hou , Gaopeng Xu , Haitao Yao

We propose a first step toward multilingual end-to-end automatic speech recognition (ASR) by integrating knowledge about speech articulators. The key idea is to leverage a rich set of fundamental units that can be defined "universally"…

Audio and Speech Processing · Electrical Eng. & Systems 2023-09-19 Hao Yen , Sabato Marco Siniscalchi , Chin-Hui Lee

Large language model (LLM)-based automatic speech recognition (ASR) achieves strong performance but often incurs high computational costs. This work investigates how to obtain the best LLM-ASR performance efficiently. Through comprehensive…

Sound · Computer Science 2025-08-07 Bingshen Mu , Yiwen Shao , Kun Wei , Dong Yu , Lei Xie

Automatic speech recognition (ASR) systems normally consist of an acoustic model (AM) and a language model (LM). The acoustic model estimates the probability distribution of text given the input speech, while the language model calibrates…

Computation and Language · Computer Science 2025-06-17 Qingliang Meng , Pengju Ren , Tian Li , Changsong Dai , Huizhi Liang

We introduce romanization encoding for script-heavy languages to optimize multilingual and code-switching Automatic Speech Recognition (ASR) systems. By adopting romanization encoding alongside a balanced concatenated tokenizer within a…

Computation and Language · Computer Science 2024-12-18 Wen Ding , Fei Jia , Hainan Xu , Yu Xi , Junjie Lai , Boris Ginsburg

Autoencoder networks are unsupervised approaches aiming at combining generative and representational properties by learning simultaneously an encoder-generator map. Although studied extensively, the issues of whether they have the same…

Machine Learning · Computer Science 2020-04-10 Stanislav Pidhorskyi , Donald Adjeroh , Gianfranco Doretto

Recently, a generative variational autoencoder (VAE) has been proposed for speech enhancement to model speech statistics. However, this approach only uses clean speech in the training phase, making the estimation particularly sensitive to…

Audio and Speech Processing · Electrical Eng. & Systems 2021-05-18 Huajian Fang , Guillaume Carbajal , Stefan Wermter , Timo Gerkmann

Recently, self-supervised learning (SSL) techniques have been introduced to solve the monaural speech enhancement problem. Due to the lack of using clean phase information, the enhancement performance is limited in most SSL methods.…

Sound · Computer Science 2021-12-22 Yi Li , Yang Sun , Syed Mohsen Naqvi

Pretrained multilingual language models (LMs) can be successfully transformed into multilingual sentence encoders (SEs; e.g., LaBSE, xMPNet) via additional fine-tuning or model distillation with parallel data. However, it remains unclear…

Computation and Language · Computer Science 2022-10-14 Ivan Vulić , Goran Glavaš , Fangyu Liu , Nigel Collier , Edoardo Maria Ponti , Anna Korhonen

We develop a large language model (LLM) based automatic speech recognition (ASR) system that can be contextualized by providing keywords as prior information in text prompts. We adopt decoder-only architecture and use our in-house LLM,…

Audio and Speech Processing · Electrical Eng. & Systems 2024-10-14 Kento Nozawa , Takashi Masuko , Toru Taniguchi

Despite the success of end-to-end automatic speech recognition (ASR) models, challenges persist in recognizing rare, out-of-vocabulary words - including named entities (NE) - and in adapting to new domains using only text data. This work…

Building scalable models to learn from diverse, multimodal data remains an open challenge. For vision-language data, the dominant approaches are based on contrastive learning objectives that train a separate encoder for each modality. While…

Computer Vision and Pattern Recognition · Computer Science 2022-10-24 Xinyang Geng , Hao Liu , Lisa Lee , Dale Schuurmans , Sergey Levine , Pieter Abbeel

Multilingual automatic speech recognition (ASR) models have shown great promise in recent years because of the simplified model training and deployment process. Conventional methods either train a universal multilingual model without taking…

Audio and Speech Processing · Electrical Eng. & Systems 2021-07-14 Long Zhou , Jinyu Li , Eric Sun , Shujie Liu

Conversational automatic speech recognition (ASR) is a task to recognize conversational speech including multiple speakers. Unlike sentence-level ASR, conversational ASR can naturally take advantages from specific characteristics of…

Sound · Computer Science 2022-02-18 Kun Wei , Yike Zhang , Sining Sun , Lei Xie , Long Ma

Building speech recognizers in multiple languages typically involves replicating a monolingual training recipe for each language, or utilizing a multi-task learning approach where models for different languages have separate output labels…

Computation and Language · Computer Science 2017-11-08 Suyoun Kim , Michael L. Seltzer