ISCA Award for Best Student Paper (students in bold)

---

---

On the Relationship between Accent Strength and Articulatory Features

Kevin Huang, Sean Foley, Jihwan Lee, Yoonjeong Lee, Dani Byrd, Shrikanth Narayanan [pdf]

Abstract: This paper explores the relationship between accent strength and articulatory features inferred from acoustic speech. To quantify accent strength, we compare phonetic transcriptions with transcriptions based on dictionary-based references, computing phoneme-level difference as a measure of accent strength. The proposed framework leverages recent self-supervised learning articulatory inversion techniques to estimate articulatory features. Analyzing a corpus of read speech from American and British English speakers, this study examines correlations between derived articulatory parameters and accent strength proxies, associating systematic articulatory differences with indexed accent strength. Results indicate that tongue positioning patterns distinguish the two dialects, with notable differences inter-dialects in rhotic and low back vowels. These findings contribute to automated accent analysis and articulatory modeling for speech processing applications.

---

OWSM v4: Improving Open Whisper-Style Speech Models via Data Scaling and Cleaning Models

Yifan Peng, Muhammad Shakeel, Yui Sudo, William Chen, Jinchuan Tian, Chyi-Jiunn Lin and Shinji Watanabe [pdf]

Abstract: The Open Whisper-style Speech Models (OWSM) project has developed a series of fully open speech foundation models using academic-scale resources, but their training data remains insufficient. This work enhances OWSM by integrating YODAS, a large-scale web-crawled dataset with a Creative Commons license. However, incorporating YODAS is nontrivial due to its wild nature, which introduces challenges such as incorrect language labels and audio-text misalignments. To address this, we develop a scalable data-cleaning pipeline using public toolkits, yielding a dataset with 166,000 hours of speech across 75 languages. Our new series of OWSM v4 models, trained on this curated dataset alongside existing OWSM data, significantly outperform previous versions on multilingual benchmarks. Our models even match or surpass frontier industrial models like Whisper and MMS in multiple scenarios. We will publicly release the cleaned YODAS data, pre-trained models, and all associated scripts via the ESPnet toolkit.

---

Attention Models and Auditory Transduction Features for Noise Robustness

Cathal Ó Faoláin and Andrew Hines [pdf]

Abstract: Human abilities surpass current speech processing systems in complex, noisy environments. While popular inputs for Automatic Speech Recognition (ASR) systems, such as raw acoustic signals and Mel spectrograms, perform well in quiet conditions, their effectiveness declines in noise. A recently developed generative WaveNet-based model emulates human auditory transduction in real time, offering alternative input features through its “IHCogram” outputs. We investigate these IHCograms across various Signal-to-Noise ratios (SNRs) using state-of-the-art feature encoders. Our findings show that IHCograms significantly enhance phoneme recognition in noisy conditions with minimal computational overhead, regardless of the model encoder used. Additionally, we introduce our Attention Feature Encoder (AFE) models, which leverage the channel structure of IHCograms and demonstrate superior size and performance compared to existing feature encoders.