9 papers
Teaching the Teachers: Boosting unsupervised domain adaptation in speech recognition by ensemble update
Rehan Ahmad, Muhammad Umar Farooq, Qihang Feng +1
Speech recognition systems often struggle with data domains that have not been included in the training. To address this, unsupervised domain adaptation has been explored with ense…
Position-invariant Fine-tuning of Speech Enhancement Models with Self-supervised Speech Representations
Amit Meghanani, Thomas Hain
Integrating front-end speech enhancement (SE) models with self-supervised learning (SSL)-based speech models is effective for downstream tasks in noisy conditions. SE models are co…
Towards a Unified Benchmark for Arabic Pronunciation Assessment: Quranic Recitation as Case Study
Yassine El Kheir, Omnia Ibrahim, Amit Meghanani +12
We present a unified benchmark for mispronunciation detection in Modern Standard Arabic (MSA) using Qur'anic recitation as a case study. Our approach lays the groundwork for advanc…
SIFT-50M: A Large-Scale Multilingual Dataset for Speech Instruction Fine-Tuning
Prabhat Pandey, Rupak Vignesh Swaminathan, K V Vijay Girish +4
We introduce SIFT (Speech Instruction Fine-Tuning), a 50M-example dataset designed for instruction fine-tuning and pre-training of speech-text large language models (LLMs). SIFT-50…
LASER: Learning by Aligning Self-supervised Representations of Speech for Improving Content-related Tasks
Amit Meghanani, Thomas Hain
Self-supervised learning (SSL)-based speech models are extensively used for full-stack speech processing. However, it has been observed that improving SSL-based speech representati…
Improving Acoustic Word Embeddings through Correspondence Training of Self-supervised Speech Representations
Amit Meghanani, Thomas Hain
Acoustic word embeddings (AWEs) are vector representations of spoken words. An effective method for obtaining AWEs is the Correspondence Auto-Encoder (CAE). In the past, the CAE me…
SCORE: Self-supervised Correspondence Fine-tuning for Improved Content Representations
Amit Meghanani, Thomas Hain
There is a growing interest in cost-effective self-supervised fine-tuning (SSFT) of self-supervised learning (SSL)-based speech models to obtain task-specific representations. Thes…
Progressive unsupervised domain adaptation for ASR using ensemble models and multi-stage training
Rehan Ahmad, Muhammad Umar Farooq, Thomas Hain
In Automatic Speech Recognition (ASR), teacher-student (T/S) training has shown to perform well for domain adaptation with small amount of training data. However, adaption without…
MUST: A Multilingual Student-Teacher Learning approach for low-resource speech recognition
Muhammad Umar Farooq, Rehan Ahmad, Thomas Hain
Student-teacher learning or knowledge distillation (KD) has been previously used to address data scarcity issue for training of speech recognition (ASR) systems. However, a limitat…