arXiv:2609.38658v1 Announce Type: cross Abstract: TTS systems with autoregressive semantic modeling have demonstrated strong zero-shot voice cloning performance and rich expressive variation, but the...
GrainSpeech is a compact speech synthesis model that uses a fixed‑receptive‑field convolutional encoder to reduce pitch, energy, and duration prediction errors by 36.0%, 17.3%, and 3.4% respectively. It introduces a Mel‑specific gradient‑variance supervision that improves fine‑scale variation while avoiding quality degradation. With only 264.8K parameters, GrainSpeech achieves 17.9× real‑time Mel generation on a microcontroller and attains UTMOS scores comparable to much larger models, using less than 1.5% of their parameters.
arXiv:2608. 08638v1 Announce Type: cross Abstract: Zero-shot text-to-speech (TTS) now supports interactive assistants, personalized media, and accessibility tools.
Recent advances in zero-shot text-to-speech (TTS) have substantially improved speech quality and voice cloning fidelity. However, many zero-shot TTS systems still depend on audio prompt transcripts at inference time.
arXiv:2606. 06907v1 Announce Type: cross Abstract: Large audio language models (LALMs) extend large language models with an audio encoder and large-scale audio data.
Text injection trains speech recognition models on unpaired text alongside paired audio. We feed the speech encoder synthetic input derived from text so the whole model learns from it. Previously, we...
arXiv:2610.34623v1 Announce Type: new Abstract: Text injection trains speech recognition models on unpaired text alongside paired audio. We feed the speech encoder synthetic input derived from text s...
arXiv:2510. 20441v2 Announce Type: replace-cross Abstract: Neural audio codecs have largely promoted the application of language models (LMs) for speech applications.
GSLM2 is a multi‑stream generative spoken language model that learns complementary speech representations at multiple abstraction levels using the SpidR 2.0 encoder and a shared‑backbone SLM with stream‑specific predictors. It improves linguistic competence and scales more efficiently than prior speech models, narrowing the performance gap with text‑based language models by about two orders of magnitude on several benchmarks. The authors release the training code and checkpoints publicly.
Uni-Stream is a unified streaming speech language model that supports both speech recognition and synthesis within a single architecture. Built on compact pretrained speech models, it processes interleaved text and speech in real time and achieves performance comparable to task‑specific models through a two‑stage training approach. The authors also introduce a data annotation pipeline for streaming training and plan to release the generated transcriptions and word‑level timestamps, while analyzing how speech and text representations occupy distinct latent spaces in the model.
FireRedAudio is a 9‑billion‑parameter audio language model that separates continuous input representations for audio understanding and speech generation, enabling a single autoregressive LLM to perform tasks such as ASR, zero‑shot TTS, Instruct TTS, and semantic/acoustic speech editing. The model uses a dedicated Audio Encoder for recognition and a RedAE‑based pathway for generation, with the LLM directly generating text or conditioning a flow‑matching DiT to produce acoustic latents. Evaluations show competitive or leading performance in multilingual ASR, content‑accurate zero‑shot TTS, strong instruction following, and significant improvements in speech editing over prior work.
arXiv:2609.14743v1 Announce Type: new Abstract: Pure speech language models often lag behind text and speech-text language models in generating coherent content, but this gap is difficult to quantify...