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

Recent advancements in reasoning language models have demonstrated remarkable performance in complex tasks, but their extended chain-of-thought reasoning process increases inference overhead. While quantization has been widely adopted to…

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…

Attention-based models have recently shown great performance on a range of tasks, such as speech recognition, machine translation, and image captioning due to their ability to summarize relevant information that expands through the entire…

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.…

Target-speaker automatic speech recognition (ASR) aims to transcribe the desired speech of a target speaker from multi-talker overlapped utterances. Most of the existing target-speaker ASR (TS-ASR) methods involve either training from…

Code-switching (CS) automatic speech recognition (ASR) faces challenges due to the language confusion resulting from accents, auditory similarity, and seamless language switches. Adaptation on the pre-trained multi-lingual model has shown…

Speech data has rich acoustic and paralinguistic information with important cues for understanding a speaker's tone, emotion, and intent, yet traditional large language models such as BERT do not incorporate this information. There has been…

This paper describes AssemblyAI's industrial-scale automatic speech recognition (ASR) system, designed to meet the requirements of large-scale, multilingual ASR serving various application needs. Our system leverages a diverse training…

The performances of automatic speech recognition (ASR) systems are usually evaluated by the metric word error rate (WER) when the manually transcribed data are provided, which are, however, expensively available in the real scenario. In…

This paper presents a comprehensive analysis of quantization techniques for optimizing Large Language Models (LLMs), specifically focusing on Post-Training Quantization (PTQ) and Quantization-Aware Training (QAT). Through empirical…

Large Language Models (LLMs) have been extensively researched and used in both academia and industry since the rise in popularity of the Transformer model, which demonstrates excellent performance in AI. However, the computational demands…

Whisper is a state-of-the-art automatic speech recognition (ASR) model (Radford et al., 2022). Although Swiss German dialects are allegedly not part of Whisper's training data, preliminary experiments showed that Whisper can transcribe…

This paper presents a novel mixed-precision quantization approach for speech foundation models that tightly integrates mixed-precision learning and quantized model parameter estimation into one single model compression stage. Experiments…

For real-world speech recognition applications, noise robustness is still a challenge. In this work, we adopt the teacher-student (T/S) learning technique using a parallel clean and noisy corpus for improving automatic speech recognition…

Text encodings from automatic speech recognition (ASR) transcripts and audio representations have shown promise in speech emotion recognition (SER) ever since. Yet, it is challenging to explain the effect of each information stream on the…

We investigate the effect of speaker localization on the performance of speech recognition systems in a multispeaker, multichannel environment. Given the speaker location information, speech separation is performed in three stages. In the…

Automatic Speech Recognition (ASR) plays a crucial role in human-machine interaction and serves as an interface for a wide range of applications. Traditionally, ASR performance has been evaluated using Word Error Rate (WER), a metric that…

Prosody plays a crucial role in speech perception, influencing both human understanding and automatic speech recognition (ASR) systems. Despite its importance, prosodic stress remains under-studied due to the challenge of efficiently…

As a popular multilingual and multitask pre-trained speech model, Whisper has the problem of curse of multilinguality. To enhance multilingual capabilities in small Whisper models, we propose DQ-Whisper, a novel joint distillation and…

Diffusion-based large language models (DLLMs) have recently attracted growing interest as an alternative to autoregressive decoders. In this work, we present an empirical study on using the diffusion-based large language model LLaDA for…