This survey paper provides a comprehensive overview of the recent advancements and
challenges in applying large language models to the field of audio signal processing. Audio …

Expanding the language coverage of speech technology has the potential to improve
access to information for many more people. However, current speech technology is …

We introduce a language modeling approach for text to speech synthesis (TTS). Specifically,
we train a neural codec language model (called Vall-E) using discrete codes derived from …

Speech neuroprostheses have the potential to restore communication to people living with
paralysis, but naturalistic speed and expressivity are elusive. Here we use high-density …

We introduce AudioLM, a framework for high-quality audio generation with long-term
consistency. AudioLM maps the input audio to a sequence of discrete tokens and casts …

Large-scale generative models such as GPT and DALL-E have revolutionized the research
community. These models not only generate high fidelity outputs, but are also generalists …

We introduce SPEAR-TTS, a multi-speaker text-to-speech (TTS) system that can be trained
with minimal supervision. By combining two types of discrete speech representations, we …

Scaling text-to-speech (TTS) to large-scale, multi-speaker, and in-the-wild datasets is
important to capture the diversity in human speech such as speaker identities, prosodies …

Large Language models (LLM) have demonstrated the capability to handle a variety of
generative tasks. This paper presents the UniAudio system, which, unlike prior task-specific …

Benchmarking initiatives support the meaningful comparison of competing solutions to
prominent problems in speech and language processing. Successive benchmarking …