Related papers: Does Whisper understand Swiss German? An automatic…

The paper describes BUT's English to German offline speech translation(ST) systems developed for IWSLT2021. They are based on jointly trained Automatic Speech Recognition-Machine Translation models. Their performances is evaluated on…

We present the Swiss Parliaments Corpus (SPC), an automatically aligned Swiss German speech to Standard German text corpus. This first version of the corpus is based on publicly available data of the Bernese cantonal parliament and consists…

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…

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…

Recent advancements in deep learning have significantly enhanced multilingual automatic speech recognition (ASR) due to the development of advanced model architectures and available large-scale multilingual datasets. Despite that,…

This paper presents the architecture and performance of a novel Multilingual Automatic Speech Recognition (ASR) system developed by the Transsion Speech Team for Track 1 of the MLC-SLM 2025 Challenge. The proposed system comprises three key…

There is an increasing interest in obtaining accurate word-level timestamps from strong automatic speech recognizers, in particular Whisper. Existing approaches either require additional training or are simply not competitive. The…

Pre-trained multilingual speech foundation models, like Whisper, have shown impressive performance across different languages. However, adapting these models to new or specific languages is computationally extensive and faces catastrophic…

Voicebots have provided a new avenue for supporting the development of language skills, particularly within the context of second language learning. Voicebots, though, have largely been geared towards native adult speakers. We sought to…

Due to the scarcity of labeled dialectal speech, audio dialect classification is a challenging task for most languages, including Swiss German. In this work, we explore the ability of large language models (LLMs) as agents in understanding…

Multilingual Automatic Speech Recognition (ASR) models are typically evaluated in a setting where the ground-truth language of the speech utterance is known, however, this is often not the case for most practical settings. Automatic Spoken…

Recent advances in automatic speech recognition (ASR) have achieved accuracy levels comparable to human transcribers, which led researchers to debate if the machine has reached human performance. Previous work focused on the English…

Speech-LLM models have demonstrated great performance in multi-modal and multi-task speech understanding. A typical speech-LLM paradigm is integrating speech modality with a large language model (LLM). While the Whisper encoder was…

This work presents a speech-to-text system "Pisets" for scientists and journalists which is based on a three-component architecture aimed at improving speech recognition accuracy while minimizing errors and hallucinations associated with…

Automatic Speech Recognition (ASR) has seen remarkable progress, with models like OpenAI Whisper and NVIDIA Canary achieving state-of-the-art (SOTA) performance in offline transcription. However, these models are not designed for streaming…

Recent years have witnessed great strides in self-supervised learning (SSL) on the speech processing. The SSL model is normally pre-trained on a great variety of unlabelled data and a large model size is preferred to increase the modeling…

Despite the recent advancements in speech recognition, there are still difficulties in accurately transcribing conversational and emotional speech in noisy and reverberant acoustic environments. This poses a particular challenge in the…

We present ASR Bundestag, a dataset for automatic speech recognition in German, consisting of 610 hours of aligned audio-transcript pairs for supervised training as well as 1,038 hours of unlabeled audio snippets for self-supervised…

ASR systems often struggle with maintaining syntactic and semantic accuracy in long audio transcripts, impacting tasks like Named Entity Recognition (NER), capitalization, and punctuation. We propose a novel approach that enhances ASR by…

While supervised quality predictors for synthesized speech have demonstrated strong correlations with human ratings, their requirement for in-domain labeled training data hinders their generalization ability to new domains. Unsupervised…