Related papers: Scaling Speech Tokenizers with Diffusion Autoencod…
Visual tokenizer is a critical component for vision generation. However, the existing tokenizers often face unsatisfactory trade-off between compression ratios and reconstruction fidelity. To fill this gap, we introduce a powerful and…
Diffusion Transformers (DiTs) achieve superior image generation quality but suffer from quadratic computational complexity relative to token count. While various token reduction (TR) methods have been proposed to mitigate this cost, they…
Speech tokenizers are essential for connecting speech to large language models (LLMs) in multimodal systems. These tokenizers are expected to preserve both semantic and acoustic information for downstream understanding and generation.…
The diffusion model is capable of generating high-quality data through a probabilistic approach. However, it suffers from the drawback of slow generation speed due to the requirement of a large number of time steps. To address this…
A good language model starts with a good tokenizer. Tokenization is especially important for speech modeling, which must handle continuous signals that mix linguistic and non-linguistic information. A speech tokenizer should extract…
It is increasingly considered that human speech perception and production both rely on articulatory representations. In this paper, we investigate whether this type of representation could improve the performances of a deep generative model…
Recently, denoising diffusion models have demonstrated remarkable performance among generative models in various domains. However, in the speech domain, the application of diffusion models for synthesizing time-varying audio faces…
Subword tokenization introduces a computational layer in language models where many distinct token sequences decode to the same surface form and preserve meaning, yet induce different internal computations. Despite this non-uniqueness,…
We introduce a text-to-speech(TTS) framework based on a neural transducer. We use discretized semantic tokens acquired from wav2vec2.0 embeddings, which makes it easy to adopt a neural transducer for the TTS framework enjoying its monotonic…
Recent success in speech representation learning enables a new way to leverage unlabeled data to train speech recognition model. In speech representation learning, a large amount of unlabeled data is used in a self-supervised manner to…
Language models (LMs) have shown superior performances in various speech generation tasks recently, demonstrating their powerful ability for semantic context modeling. Given the intrinsic similarity between speech generation and speech…
We propose a speaker-attributed (SA) Whisper-based model for multi-talker speech recognition that combines target-speaker modeling with serialized output training (SOT). Our approach leverages a Diarization-Conditioned Whisper (DiCoW)…
Generative AI, powered by large language models (LLMs), has revolutionized applications across text, audio, images, and video. This study focuses on developing and evaluating encoder-decoder architectures for the American Sign Language…
Recent high-performance transformer-based speech enhancement models demonstrate that time domain methods could achieve similar performance as time-frequency domain methods. However, time-domain speech enhancement systems typically receive…
A judicious combination of dictionary learning methods, block sparsity and source recovery algorithm are used in a hierarchical manner to identify the noises and the speakers from a noisy conversation between two people. Conversations are…
Training monolingual language models for low and mid-resource languages is made challenging by limited and often inadequate pretraining data. In this study, we propose a novel model conversion strategy to address this issue, adapting…
This article introduces AnCoGen, a novel method that leverages a masked autoencoder to unify the analysis, control, and generation of speech signals within a single model. AnCoGen can analyze speech by estimating key attributes, such as…
Speech-to-text translation has many potential applications for low-resource languages, but the typical approach of cascading speech recognition with machine translation is often impossible, since the transcripts needed to train a speech…
Recent advancements in end-to-end neural speech codecs enable compressing audio at extremely low bitrates while maintaining high-fidelity reconstruction. Meanwhile, low computational complexity and low latency are crucial for real-time…
Generative diffusion models have emerged as leading models in speech and image generation. However, in order to perform well with a small number of denoising steps, a costly tuning of the set of noise parameters is needed. In this work, we…