Topic: speech

A new project called Backwords uses AI to teach users how to speak in reverse, aiming to explore linguistic abilities and the capabilities of AI in language manipulation. This initiative highlights advancements in AI technology and offers an engaging way to understand reverse speech patterns.

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↗

Block's AI lab introduced Dessa, a full-duplex speech model trained solely on human conversation audio and designed to run locally on a MacBook Pro M4 Max. The release highlights advancements in privacy-focused AI models that process and generate speech directly from local devices without cloud dependency.

Ollama released version 0.40.13 of its LFM3 models, enabling text-to-speech functionality on both Linux and Windows in addition to existing platforms, expanding accessibility for users across different operating systems. This update is significant as it broadens the user base and compatibility of Liquid AI's advanced language models.

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↗

Ollama v0.40.11 adds speech functionality on macOS, allowing text-to-speech generation during model runs and supporting audio streaming via the API, enhancing accessibility and user experience. This update is significant as it broadens Ollama's capabilities, making it more versatile for various applications.