Search Results for author:
Found 31 papers, 13 papers with code
Zero-Shot Streaming Text to Speech Synthesis with Transducer and Auto-Regressive Modeling
Zero-shot streaming text-to-speech is an important research topic in human-computer interaction.
OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learning
OpenAI's CLIP, released in early 2021, have long been the go-to choice of vision encoder for building multimodal foundation models.
Pseudo-Autoregressive Neural Codec Language Models for Efficient Zero-Shot Text-to-Speech Synthesis
Building on PAR, we propose PALLE, a two-stage TTS system that leverages PAR for initial generation followed by NAR refinement.
FELLE: Autoregressive Speech Synthesis with Token-Wise Coarse-to-Fine Flow Matching
To advance continuous-valued token modeling and temporal-coherence enforcement, we propose FELLE, an autoregressive model that integrates language modeling with token-wise flow matching.
CLIPS: An Enhanced CLIP Framework for Learning with Synthetic Captions
Previous works show that noisy, web-crawled image-text pairs may limit vision-language pretraining like CLIP and propose learning with synthetic captions as a promising alternative.
Isochrony-Controlled Speech-to-Text Translation: A study on translating from Sino-Tibetan to Indo-European Languages
End-to-end speech translation (ST), which translates source language speech directly into target language text, has garnered significant attention in recent years.
Autoregressive Speech Synthesis without Vector Quantization
We present MELLE, a novel continuous-valued token based language modeling approach for text-to-speech synthesis (TTS).
E2 TTS: Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS
This paper introduces Embarrassingly Easy Text-to-Speech (E2 TTS), a fully non-autoregressive zero-shot text-to-speech system that offers human-level naturalness and state-of-the-art speaker similarity and intelligibility.
VALL-E R: Robust and Efficient Zero-Shot Text-to-Speech Synthesis via Monotonic Alignment
With the help of discrete neural audio codecs, large language models (LLM) have increasingly been recognized as a promising methodology for zero-shot Text-to-Speech (TTS) synthesis.
VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizers
This paper introduces VALL-E 2, the latest advancement in neural codec language models that marks a milestone in zero-shot text-to-speech synthesis (TTS), achieving human parity for the first time.
Boosting Diffusion Model for Spectrogram Up-sampling in Text-to-speech: An Empirical Study
Scaling text-to-speech (TTS) with autoregressive language model (LM) to large-scale datasets by quantizing waveform into discrete speech tokens is making great progress to capture the diversity and expressiveness in human speech, but the speech reconstruction quality from discrete speech token is far from satisfaction depending on the compressed speech token compression ratio.
NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models
Specifically, 1) we design a neural codec with factorized vector quantization (FVQ) to disentangle speech waveform into subspaces of content, prosody, timbre, and acoustic details; 2) we propose a factorized diffusion model to generate attributes in each subspace following its corresponding prompt.
Making Flow-Matching-Based Zero-Shot Text-to-Speech Laugh as You Like
In this work, we propose ELaTE, a zero-shot TTS that can generate natural laughing speech of any speaker based on a short audio prompt with precise control of laughter timing and expression.
MLLMs-Augmented Visual-Language Representation Learning
Visual-language pre-training has achieved remarkable success in many multi-modal tasks, largely attributed to the availability of large-scale image-text datasets.
DREAM+: Efficient Dataset Distillation by Bidirectional Representative Matching
Dataset distillation plays a crucial role in creating compact datasets with similar training performance compared with original large-scale ones.
PromptTTS 2: Describing and Generating Voices with Text Prompt
TTS approaches based on the text prompt face two main challenges: 1) the one-to-many problem, where not all details about voice variability can be described in the text prompt, and 2) the limited availability of text prompt datasets, where vendors and large cost of data labeling are required to write text prompts for speech.
NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers
To enhance the zero-shot capability that is important to achieve diverse speech synthesis, we design a speech prompting mechanism to facilitate in-context learning in the diffusion model and the duration/pitch predictor.
Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling
We propose a cross-lingual neural codec language model, VALL-E X, for cross-lingual speech synthesis.
FoundationTTS: Text-to-Speech for ASR Customization with Generative Language Model
Neural text-to-speech (TTS) generally consists of cascaded architecture with separately optimized acoustic model and vocoder, or end-to-end architecture with continuous mel-spectrograms or self-extracted speech frames as the intermediate representations to bridge acoustic model and vocoder, which suffers from two limitations: 1) the continuous acoustic frames are hard to predict with phoneme only, and acoustic information like duration or pitch is also needed to solve the one-to-many problem, which is not easy to scale on large scale and noise datasets; 2) to achieve diverse speech output based on continuous speech features, complex VAE or flow-based models are usually required.
DREAM: Efficient Dataset Distillation by Representative Matching
Although there are various matching objectives, currently the strategy for selecting original images is limited to naive random sampling.
Improving Contextual Spelling Correction by External Acoustics Attention and Semantic Aware Data Augmentation
To solve above limitations, in this paper we propose an improved non-autoregressive (NAR) spelling correction model for contextual biasing in E2E neural transducer-based ASR systems to improve the previous CSC model from two perspectives: Firstly, we incorporate acoustics information with an external attention as well as text hypotheses into CSC to better distinguish target phrase from dissimilar or irrelevant phrases.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers
In addition, we find Vall-E could preserve the speaker's emotion and acoustic environment of the acoustic prompt in synthesis.
RetrieverTTS: Modeling Decomposed Factors for Text-Based Speech Insertion
In the proposed paradigm, global and local factors in speech are explicitly decomposed and separately manipulated to achieve high speaker similarity and continuous prosody.
NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Quality
In this paper, we answer these questions by first defining the human-level quality based on the statistical significance of subjective measure and introducing appropriate guidelines to judge it, and then developing a TTS system called NaturalSpeech that achieves human-level quality on a benchmark dataset.
Ranked #1 on
Text-To-Speech Synthesis
on LJSpeech
(using extra training data)
Mixed-Phoneme BERT: Improving BERT with Mixed Phoneme and Sup-Phoneme Representations for Text to Speech
However, the works apply pre-training with character-based units to enhance the TTS phoneme encoder, which is inconsistent with the TTS fine-tuning that takes phonemes as input.
Towards Contextual Spelling Correction for Customization of End-to-end Speech Recognition Systems
In this work, we introduce a novel approach to do contextual biasing by adding a contextual spelling correction model on top of the end-to-end ASR system.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
DelightfulTTS: The Microsoft Speech Synthesis System for Blizzard Challenge 2021
The goal of this challenge is to synthesize natural and high-quality speech from text, and we approach this goal in two perspectives: The first is to directly model and generate waveform in 48 kHz sampling rate, which brings higher perception quality than previous systems with 16 kHz or 24 kHz sampling rate; The second is to model the variation information in speech through a systematic design, which improves the prosody and naturalness.
A Light-weight contextual spelling correction model for customizing transducer-based speech recognition systems
We incorporate the context information into the spelling correction model with a shared context encoder and use a filtering algorithm to handle large-size context lists.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
AdaSpeech: Adaptive Text to Speech for Custom Voice
2) To better trade off the adaptation parameters and voice quality, we introduce conditional layer normalization in the mel-spectrogram decoder of AdaSpeech, and fine-tune this part in addition to speaker embedding for adaptation.
Developing RNN-T Models Surpassing High-Performance Hybrid Models with Customization Capability
Because of its streaming nature, recurrent neural network transducer (RNN-T) is a very promising end-to-end (E2E) model that may replace the popular hybrid model for automatic speech recognition.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Neural Speech Synthesis with Transformer Network
Although end-to-end neural text-to-speech (TTS) methods (such as Tacotron2) are proposed and achieve state-of-the-art performance, they still suffer from two problems: 1) low efficiency during training and inference; 2) hard to model long dependency using current recurrent neural networks (RNNs).
Ranked #9 on
Text-To-Speech Synthesis
on LJSpeech
(using extra training data)
