Related papers: Expressive, Variable, and Controllable Duration Mo…
We present a novel generative model that combines state-of-the-art neural text-to-speech (TTS) with semi-supervised probabilistic latent variable models. By providing partial supervision to some of the latent variables, we are able to force…
This work presents a lifelong learning approach to train a multilingual Text-To-Speech (TTS) system, where each language was seen as an individual task and was learned sequentially and continually. It does not require pooled data from all…
Forecasting conditional stochastic nonlinear dynamical systems is a fundamental challenge repeatedly encountered across the biological and physical sciences. While flow-based models can impressively predict the temporal evolution of…
Non-autoregressive text to speech (NAR-TTS) models have attracted much attention from both academia and industry due to their fast generation speed. One limitation of NAR-TTS models is that they ignore the correlation in time and frequency…
Speaker diarization systems often struggle with high intrinsic intra-speaker variability, such as shifts in emotion, health, or content. This can cause segments from the same speaker to be misclassified as different individuals, for…
Temporal reasoning over long, multi-session dialogues is a critical capability for conversational agents. However, existing works and our pilot study have shown that as dialogue histories grow in length and accumulate noise, current…
With the rapid advancement in deep generative models, recent neural Text-To-Speech(TTS) models have succeeded in synthesizing human-like speech. There have been some efforts to generate speech with various prosody beyond monotonous prosody…
Recent advances in Text-to-Speech (TTS) have improved quality and naturalness to near-human capabilities when considering isolated sentences. But something which is still lacking in order to achieve human-like communication is the dynamic…
Controllable TTS models with natural language prompts often lack the ability for fine-grained control and face a scarcity of high-quality data. We propose a two-stage style-controllable TTS system with language models, utilizing a quantized…
We introduce TiCo, a time-controllable spoken dialogue model (SDM) that follows time-constrained instructions (e.g., "Please generate a response lasting about 15 seconds") and generates spoken responses with controllable duration. This…
Recent parallel neural text-to-speech (TTS) synthesis methods are able to generate speech with high fidelity while maintaining high performance. However, these systems often lack control over the output prosody, thus restricting the…
Large-scale latent diffusion models (LDMs) excel in content generation across various modalities, but their reliance on phonemes and durations in text-to-speech (TTS) limits scalability and access from other fields. While recent studies…
This paper proposes methods of predicting dynamic time series (including non-stationary ones) based on a linguistic approach, namely, the study of occurrences and repetition of so-called N-grams. This approach is used in computational…
Pretrained language models (PTLMs) are typically learned over a large, static corpus and further fine-tuned for various downstream tasks. However, when deployed in the real world, a PTLM-based model must deal with data distributions that…
Current non-autoregressive (NAR) text-to-speech (TTS) systems still struggle to model diverse and speaker-dependent duration variation. We further observe that richer duration variation can increase the synthesis difficulty of existing…
Diffusion models have attracted a lot of attention in recent years. These models view speech generation as a continuous-time process. For efficient training, this process is typically restricted to additive Gaussian noising, which is…
Speech conveys more information than text, as the same word can be uttered in various voices to convey diverse information. Compared to traditional text-to-speech (TTS) methods relying on speech prompts (reference speech) for voice…
Masked language modeling is a widely used method for learning language representations, where the model predicts a randomly masked word in each input. However, this approach typically considers only a single correct answer during training,…
Acoustics-to-word models are end-to-end speech recognizers that use words as targets without relying on pronunciation dictionaries or graphemes. These models are notoriously difficult to train due to the lack of linguistic knowledge. It is…
Continual learning has emerged as an increasingly important challenge across various tasks, including Spoken Language Understanding (SLU). In SLU, its objective is to effectively handle the emergence of new concepts and evolving…