6 papers · 1 filter
Frame-Stacked Local Transformers For Efficient Multi-Codebook Speech Generation
Roy Fejgin, Paarth Neekhara, Xuesong Yang +6
Speech generation models based on large language models (LLMs) typically operate on discrete acoustic codes, which differ fundamentally from text tokens due to their multicodebook…
HiFiTTS-2: A Large-Scale High Bandwidth Speech Dataset
Ryan Langman, Xuesong Yang, Paarth Neekhara +4
This paper introduces HiFiTTS-2, a large-scale speech dataset designed for high-bandwidth speech synthesis. The dataset is derived from LibriVox audiobooks, and contains approximat…
NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference
Edresson Casanova, Paarth Neekhara, Ryan Langman +6
Large Language Models (LLMs) have significantly advanced audio processing by leveraging audio codecs to discretize audio into tokens, enabling the application of language modeling…
Spectral Codecs: Improving Non-Autoregressive Speech Synthesis with Spectrogram-Based Audio Codecs
Ryan Langman, Ante JukiÄ, Kunal Dhawan +2
Historically, most speech models in machine-learning have used the mel-spectrogram as a speech representation. Recently, discrete audio tokens produced by neural audio codecs have…
TTS-Transducer: End-to-End Speech Synthesis with Neural Transducer
Vladimir Bataev, Subhankar Ghosh, Vitaly Lavrukhin +1
This work introduces TTS-Transducer - a novel architecture for text-to-speech, leveraging the strengths of audio codec models and neural transducers. Transducers, renowned for thei…
Low Frame-rate Speech Codec: a Codec Designed for Fast High-quality Speech LLM Training and Inference
Edresson Casanova, Ryan Langman, Paarth Neekhara +5
Large language models (LLMs) have significantly advanced audio processing through audio codecs that convert audio into discrete tokens, enabling the application of language modelin…