Topic: asr

Researchers have developed a new interface using contextual pictograms to help identify and correct speech transcription errors in multilingual Automatic Speech Recognition systems, addressing the challenge of recognizing unfamiliar or visually similar word hypotheses. This tool is crucial as it enhances accuracy in ASR systems used across multiple languages.

arxiv.org↗

NVIDIA released Nemotron 3.5 Transcribe, an open-weights speech LLM with 40-language transcription capabilities and improved accuracy metrics. This model marks a step forward in multilingual speech recognition technology.

A new large-scale corpus called Lipi-Ghor has been created for Bengali speech, addressing the under-resourcing issue in spoken language research by providing extensive, diarized, multi-domain audio. This corpus is significant as it offers a substantial dataset for improving Bengali speech recognition technologies.

arxiv.org↗

Researchers propose a smart subset selection method for fine-tuning ASR models like Whisper, reducing the need for extensive transcribed data and lowering costs. This approach is crucial as it enhances accessibility and efficiency in improving speech recognition quality without the high expense of full dataset fine-tuning.

arxiv.org↗