Related papers: Whilter: A Whisper-based Data Filter for "In-the-W…

We demonstrate that carefully adjusting the tokenizer of the Whisper speech recognition model significantly improves the precision of word-level timestamps when applying dynamic time warping to the decoder's cross-attention scores. We…

Recent advancements in Automatic Speech Recognition (ASR) systems, exemplified by Whisper, have demonstrated the potential of these systems to approach human-level performance given sufficient data. However, this progress doesn't readily…

This work investigates two strategies for zero-shot non-intrusive speech assessment leveraging large language models. First, we explore the audio analysis capabilities of GPT-4o. Second, we propose GPT-Whisper, which uses Whisper as an…

In recent years, much speech separation research has focused primarily on improving model performance. However, for low-latency speech processing systems, high efficiency is equally important. Therefore, we propose a speech separation model…

This work presents a suite of fine-tuned Whisper models for Swedish, trained on a dataset of unprecedented size and variability for this mid-resourced language. As languages of smaller sizes are often underrepresented in multilingual…

Deepfake speech utterances can be forged by replacing one or more words in a bona fide utterance with semantically different words synthesized with speech-generative models. While a dedicated synthetic word detector could be developed, we…

Recent work on distilling Whisper's knowledge into small models using pseudo-labels shows promising performance while reducing the size by up to 50%. This results in small, efficient, and dedicated models. However, a critical step of…

A crucial part of an accurate and reliable spoken language assessment system is the underlying ASR model. Recently, large-scale pre-trained ASR foundation models such as Whisper have been made available. As the output of these models is…

Speaker verification is a task of confirming an individual's identity through the analysis of their voice. Whispered speech differs from phonated speech in acoustic characteristics, which degrades the performance of speaker verification…

Recent multi-modal models have shown remarkable versatility in real-world applications. However, their rapid development encounters two critical data challenges. First, the training process requires large-scale datasets, leading to…

Integrating named entity recognition (NER) with automatic speech recognition (ASR) can significantly enhance transcription accuracy and informativeness. In this paper, we introduce WhisperNER, a novel model that allows joint speech…

This paper presents a new approach to fine-tuning OpenAI's Whisper model for low-resource languages by introducing a novel data generation method that converts sentence-level data into a long-form corpus, using Swiss German as a case study.…

We propose WHISPER-GPT: A generative large language model (LLM) for speech and music that allows us to work with continuous audio representations and discrete tokens simultaneously as part of a single architecture. There has been a huge…

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…

Crowdsourcing has been the prevalent paradigm for creating natural language understanding datasets in recent years. A common crowdsourcing practice is to recruit a small number of high-quality workers, and have them massively generate…

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…

Traditional Text-to-Speech (TTS) systems rely on studio-quality speech recorded in controlled settings.a Recently, an effort known as noisy-TTS training has emerged, aiming to utilize in-the-wild data. However, the lack of dedicated…

In this paper, we explore the untapped potential of Whisper, a well-established automatic speech recognition (ASR) foundation model, in the context of L2 spoken language assessment (SLA). Unlike prior studies that extrinsically analyze…

The growing prevalence of real-world deepfakes presents a critical challenge for existing detection systems, which are often evaluated on datasets collected just for scientific purposes. To address this gap, we introduce a novel dataset of…

Audio-Visual Speech Recognition (AVSR) uses lip-based video to improve performance in noise. Since videos are harder to obtain than audio, the video training data of AVSR models is usually limited to a few thousand hours. In contrast,…