Related papers: Quantization for OpenAI's Whisper Models: A Compar…

The automated classification of stuttered speech has significant implications for timely assessments providing assistance to speech language pathologists. Despite notable advancements in the field, the cases in which multiple disfluencies…

Speech impairments caused by conditions such as cerebral palsy or genetic disorders pose significant challenges for automatic speech recognition (ASR) systems. Despite recent advances, ASR models like Whisper struggle with non-normative…

Fine-tuning multilingual ASR models like Whisper for low-resource languages often improves read speech but degrades spontaneous audio performance, a phenomenon we term studio-bias. To diagnose this mismatch, we introduce Vividh-ASR, a…

Speech enhancement (SE) systems are typically evaluated using a variety of instrumental metrics. The use of automatic speech recognition (ASR) systems to evaluate SE performance is common in literature, usually in terms of word error rate…

High-quality automatic speech recognition (ASR) is essential for virtual assistants (VAs) to work well. However, ASR often performs poorly on VA requests containing named entities. In this work, we start from the observation that many ASR…

In this paper, we summarize the application of transformer and its streamable variant, Emformer based acoustic model for large scale speech recognition applications. We compare the transformer based acoustic models with their LSTM…

Large-scale multilingual ASR models like Whisper excel in high-resource settings but face challenges in low-resource scenarios, such as rare languages and code-switching (CS), due to computational costs and catastrophic forgetting. We…

Trained on 680,000 hours of massive speech data, Whisper is a multitasking, multilingual speech foundation model demonstrating superior performance in automatic speech recognition, translation, and language identification. However, its…

We consider the problem of recognizing speech utterances spoken to a device which is generating a known sound waveform; for example, recognizing queries issued to a digital assistant which is generating responses to previous user inputs.…

It is well known that many machine learning systems demonstrate bias towards specific groups of individuals. This problem has been studied extensively in the Facial Recognition area, but much less so in Automatic Speech Recognition (ASR).…

Pre-training speech models on large volumes of data has achieved remarkable success. OpenAI Whisper is a multilingual multitask model trained on 680k hours of supervised speech data. It generalizes well to various speech recognition and…

The growing use of large language models has raised environmental and economic concerns about their intensity of resource usage during inference. Serving these models to each user requires substantial energy and water for cooling. Model…

We describe a system that generates speaker-annotated transcripts of meetings by using a virtual microphone array, a set of spatially distributed asynchronous recording devices such as laptops and mobile phones. The system is composed of…

It is estimated that around 70 million people worldwide are affected by a speech disorder called stuttering. With recent advances in Automatic Speech Recognition (ASR), voice assistants are increasingly useful in our everyday lives. Many…

Large reasoning models (LRMs) have demonstrated remarkable proficiency in tackling complex tasks through step-by-step thinking. However, this lengthy reasoning process incurs substantial computational and latency overheads, hindering the…

Language models play a central role in automatic speech recognition (ASR), yet most methods rely on text-only models unaware of ASR error patterns. Recently, large language models (LLMs) have been applied to ASR correction, but introduce…

Modern speech enhancement algorithms achieve remarkable noise suppression by means of large recurrent neural networks (RNNs). However, large RNNs limit practical deployment in hearing aid hardware (HW) form-factors, which are battery…

Improving the deployment efficiency of transformer-based language models has been challenging given their high computation and memory cost. While INT8 quantization has recently been shown to be effective in reducing both the memory cost and…

This paper presents a streaming speaker-attributed automatic speech recognition (SA-ASR) model that can recognize ``who spoke what'' with low latency even when multiple people are speaking simultaneously. Our model is based on token-level…

Whisper, the recently developed multilingual weakly supervised model, is reported to perform well on multiple speech recognition benchmarks in both monolingual and multilingual settings. However, it is not clear how Whisper would fare under…