Latest Articles for Speech Recognition

Audio and Speech Processing Design Choices Impacting Speech Model Performance

A study on how design choices affect speech foundation models.

Li-Wei Chen, Takuya Higuchi, He Bai

2025-06-10T06:00:35+00:00 ― 7 min read

Audio and Speech Processing Improving Speech Recognition for Accents

This article discusses methods to enhance speech recognition for accented speech.

Francesco Nespoli, Daniel Barreda, Patrick A. Naylor

2025-06-08T12:42:50+00:00 ― 6 min read

Computation and Language Improving Audio Language Models for Thai and English

This study addresses challenges in audio language models for low-resource languages.

Potsawee Manakul, Guangzhi Sun, Warit Sirichotedumrong

2025-06-08T08:39:55+00:00 ― 5 min read

Audio and Speech Processing Improving TTS Systems for Indian Languages

Enhancing speech synthesis in Indian languages using inter-pausal units.

Anusha Prakash, Hema A Murthy

2025-06-08T02:59:50+00:00 ― 6 min read

Sound Advancing Automatic Speech Recognition with CADA-GAN

CADA-GAN enhances ASR systems' performance across various recording environments.

Chien-Chun Wang, Li-Wei Chen, Cheng-Kang Chou

2025-06-07T23:45:30+00:00 ― 6 min read

Computer Vision and Pattern Recognition Advancements in Audio-Visual Speech Recognition

Llama-AVSR merges audio and visual inputs for enhanced speech recognition accuracy.

Umberto Cappellazzo, Minsu Kim, Honglie Chen

2025-06-07T18:05:25+00:00 ― 6 min read

Sound Advancements in Language Learning Feedback Systems

A new method uses virtual shadowing to enhance language learners' pronunciation feedback.

Haopeng Geng, Daisuke Saito, Nobuaki Minematsu

2025-06-07T05:56:40+00:00 ― 6 min read

Machine Learning Advancements in Speech Recognition for Children

A new ASR method helps technology understand children's speech better.

Zhonghao Shi, Harshvardhan Srivastava, Xuan Shi

2025-06-06T20:13:40+00:00 ― 5 min read

Computer Vision and Pattern Recognition New System Combines Sound and Vision for Object Recognition

YOSS uses audio to improve object identification in images.

Wenhao Yang, Jianguo Wei, Wenhuan Lu

2025-06-05T10:22:06+00:00 ― 4 min read

Audio and Speech Processing Building Better Speech Datasets for Under-Served Languages

A project developing speech and text datasets for languages with limited resources.

Nikola Ljubešić, Peter Rupnik, Danijel Koržinek

2025-06-04T06:41:20+00:00 ― 5 min read

Audio and Speech Processing Improving Speaker Verification with CA-MHFA

A new framework enhances voice recognition and adapts to various speech tasks.

Junyi Peng, Ladislav Mošner, Lin Zhang

2025-06-04T05:52:45+00:00 ― 4 min read

Computation and Language Advancements in Textless Speech Processing Techniques

New methods improve speech recognition for low-resource languages without text.

Krithiga Ramadass, Abrit Pal Singh, Srihari J

2025-06-03T18:32:35+00:00 ― 4 min read

Computation and Language Improving Speech Recognition Through Phonetic Techniques

New methods enhance accuracy in speech recognition systems using phonetic understanding.

Leonid Velikovich, Christopher Li, Diamantino Caseiro

2025-06-03T16:55:25+00:00 ― 5 min read

Sound Improving Speech Recognition with Human-Inspired Features

New acoustic features enhance ASR systems' performance in noisy environments.

Muhammad A. Shah, Bhiksha Raj

2025-06-03T14:29:40+00:00 ― 4 min read

Audio and Speech Processing Whisper-Medusa: Advancing Speech Recognition Efficiency

New model achieves faster speech transcription without sacrificing accuracy.

Yael Segal-Feldman, Aviv Shamsian, Aviv Navon

2025-06-03T00:43:45+00:00 ― 4 min read

Audio and Speech Processing Matryoshka Speaker Embeddings: A Flexible Approach to Voice Recognition

Discover how Matryoshka embeddings improve speaker recognition efficiency and flexibility.

Shuai Wang, Pengcheng Zhu, Haizhou Li

2025-06-02T20:40:50+00:00 ― 4 min read

Sound Advancements in Text-to-Speech Adaptation

New model VoiceGuider improves TTS for diverse speakers.

Jiheum Yeom, Heeseung Kim, Jooyoung Choi

2025-06-02T19:03:40+00:00 ― 6 min read

Audio and Speech Processing Advancements in Speech Recognition Technology

A new method improves speech recognition for long recordings.

Hao Yen, Shaoshi Ling, Guoli Ye

2025-05-30T21:54:17+00:00 ― 5 min read

Audio and Speech Processing Advancements in Speech Language Models Without Extensive Training Data

New method for speech language models reduces need for extensive data.

Ke-Han Lu, Zhehuai Chen, Szu-Wei Fu

2025-05-29T17:50:26+00:00 ― 6 min read

Audio and Speech Processing The Evolution of Speaker Diarization

How new methods are transforming speaker identification in audio recordings.

Petr Pálka, Federico Landini, Dominik Klement

2025-05-25T18:57:25+00:00 ― 6 min read

Sound Target Speaker Extraction: Enhancing Clarity in Noisy Settings

Learn how TSE improves speech recognition in crowded environments using text cues.

Ziyang Jiang, Xinyuan Qian, Jiahe Lei

2025-05-25T00:14:51+00:00 ― 6 min read

Audio and Speech Processing Using Voice Assistants to Detect Mild Cognitive Impairment

Voice assistants help identify early signs of memory issues in older adults.

Nana Lin, Youxiang Zhu, Xiaohui Liang

2025-05-24T01:31:44+00:00 ― 7 min read

Sound Mamba: Advancing Speech Recognition Technology

Mamba enhances speech recognition with speed and accuracy, reshaping interaction with devices.

Yoshiki Masuyama, Koichi Miyazaki, Masato Murata

2025-05-19T22:39:54+00:00 ― 4 min read

Sound Using Visual Cues to Clear Up Speech in Noise

New method enhances speech clarity using visual information from surroundings.

Xinyuan Qian, Jiaran Gao, Yaodan Zhang

2025-05-18T20:42:14+00:00 ― 5 min read

Sound SAMOS: Advancing Speech Quality Assessment

SAMOS offers a new way to measure speech quality, enhancing naturalness.

Yu-Fei Shi, Yang Ai, Ye-Xin Lu

2025-05-11T19:57:24+00:00 ― 6 min read

Sound Tiny-Align: A New Approach to Voice Assistants

Tiny-Align enhances voice assistants for better personal interaction on small devices.

Ruiyang Qin, Dancheng Liu, Gelei Xu

2025-05-07T01:43:40+00:00 ― 6 min read

Machine Learning VQalAttent: A New Approach to Speech Generation

Introducing VQalAttent, a simpler model for generating realistic machine speech.

Armani Rodriguez, Silvija Kokalj-Filipovic

2025-05-05T05:35:38+00:00 ― 5 min read

Audio and Speech Processing United-MedASR: Improving Medical Speech Recognition

A new ASR system enhances medical speech recognition for accurate patient care.

Sourav Banerjee, Ayushi Agarwal, Promila Ghosh

2025-04-30T00:58:50+00:00 ― 6 min read

Sound Detecting Deepfakes: The Role of ASR Models

Exploring how ASR models help identify speech deepfakes effectively.

Davide Salvi, Amit Kumar Singh Yadav, Kratika Bhagtani

2025-04-24T01:54:40+00:00 ― 7 min read

Computation and Language A New Method for Speaker-Attributed Speech Recognition

Efficiently tracks speakers in multilingual settings using automatic speech recognition.

Thai-Binh Nguyen, Alexander Waibel

2025-04-20T15:33:18+00:00 ― 6 min read

Audio and Speech Processing Advancing Speech Recognition for Dysfluency

Improving machine transcription for better understanding of speech disorders.

Jiachen Lian, Xuanru Zhou, Zoe Ezzes

2025-04-17T08:35:42+00:00 ― 5 min read

Computation and Language Enhancing Speech Recognition with Pinyin

New model improves Chinese speech recognition accuracy significantly.

Junhong Liang

2025-04-15T08:10:03+00:00 ― 6 min read

Sound Introducing Noro: A Reliable Voice Conversion System

Noro enhances voice conversion, making it effective even in noisy settings.

Haorui He, Yuchen Song, Yuancheng Wang

2025-04-15T07:14:42+00:00 ― 6 min read

Computation and Language GLM-4-Voice: The Next Step in Chatbots

A new chatbot offering human-like conversations with emotional awareness.

Aohan Zeng, Zhengxiao Du, Mingdao Liu

2025-04-02T18:12:36+00:00 ― 3 min read

Computation and Language Transforming Speech Recognition: New Evaluation Methods

Discover how style-agnostic evaluation improves Automatic Speech Recognition systems.

Quinten McNamara, Miguel Ángel del Río Fernández, Nishchal Bhandari

2025-03-26T13:05:15+00:00 ― 7 min read

Computation and Language Adaptive Dropout: Streamlining Speech Recognition Models

Learn how adaptive dropout improves efficiency in speech recognition systems.

Yotaro Kubo, Xingyu Cai, Michiel Bacchiani

2025-03-22T10:47:06+00:00 ― 7 min read

Computation and Language Can AI Talk to Kids? Exploring Language Models

Research tests AI's ability to communicate with children like caregivers.

Jing Liu, Abdellah Fourtassi

2025-03-15T21:53:33+00:00 ― 6 min read

Computation and Language Say Goodbye to LaTeX Struggles: Speak Your Equations

A speech-to-text tool transforms spoken math into LaTeX effortlessly.

Evangelia Gkritzali, Panagiotis Kaliosis, Sofia Galanaki

2025-03-09T16:48:54+00:00 ― 6 min read

Sound LatentSpeech: A Step Forward in Text-to-Speech

Revolutionizing text-to-speech with improved efficiency and natural-sounding voices.

Haowei Lou, Helen Paik, Pari Delir Haghighi

2025-03-06T14:47:24+00:00 ― 6 min read

Sound Advancements in Speech Recognition for Persian Digits

Speech recognition technology enhances digit recognition, especially in noisy environments.

Ali Nasr-Esfahani, Mehdi Bekrani, Roozbeh Rajabi

2025-02-27T00:11:42+00:00 ― 5 min read