23 citations · 23 across the 9 of their papers we have counts for
12 papers
Cluster, Route, Escalate: Cascaded Framework for Cost-Aware LLM Serving
Yasmin Moslem, Magdalena Kacmajor, Vasudevan Nedumpozhimana +11
Efficient deployment of large language models (LLMs) in production forces a trade-off between accuracy and cost. Operators often default to a single model that is either expensive…
BASE TTS: Lessons from building a billion-parameter Text-to-Speech model on 100K hours of data
Mateusz Łajszczak, Guillermo Cámbara, Yang Li +16
We introduce a text-to-speech (TTS) model called BASE TTS, which stands for ig daptive treamable TTS with mergent abilities. BASE TT…
Comparing normalizing flows and diffusion models for prosody and acoustic modelling in text-to-speech
Guangyan Zhang, Thomas Merritt, Manuel Sam Ribeiro +10
Neural text-to-speech systems are often optimized on L1/L2 losses, which make strong assumptions about the distributions of the target data space. Aiming to improve those assumptio…
Controllable Emphasis with zero data for text-to-speech
Arnaud Joly, Marco Nicolis, Ekaterina Peterova +11
We present a scalable method to produce high quality emphasis for text-to-speech (TTS) that does not require recordings or annotations. Many TTS models include a phoneme duration m…
eCat: An End-to-End Model for Multi-Speaker TTS & Many-to-Many Fine-Grained Prosody Transfer
Ammar Abbas, Sri Karlapati, Bastian Schnell +7
We present eCat, a novel end-to-end multispeaker model capable of: a) generating long-context speech with expressive and contextually appropriate prosody, and b) performing fine-gr…
Simple and Effective Multi-sentence TTS with Expressive and Coherent Prosody
Peter Makarov, Ammar Abbas, Mateusz Łajszczak +5
Generating expressive and contextually appropriate prosody remains a challenge for modern text-to-speech (TTS) systems. This is particularly evident for long, multi-sentence inputs…
Expressive, Variable, and Controllable Duration Modelling in TTS
Ammar Abbas, Thomas Merritt, Alexis Moinet +5
Duration modelling has become an important research problem once more with the rise of non-attention neural text-to-speech systems. The current approaches largely fall back to rely…
CopyCat2: A Single Model for Multi-Speaker TTS and Many-to-Many Fine-Grained Prosody Transfer
Sri Karlapati, Penny Karanasou, Mateusz Lajszczak +7
In this paper, we present CopyCat2 (CC2), a novel model capable of: a) synthesizing speech with different speaker identities, b) generating speech with expressive and contextually…
Multi-Scale Spectrogram Modelling for Neural Text-to-Speech
Ammar Abbas, Bajibabu Bollepalli, Alexis Moinet +6
We propose a novel Multi-Scale Spectrogram (MSS) modelling approach to synthesise speech with an improved coarse and fine-grained prosody. We present a generic multi-scale spectrog…
A learned conditional prior for the VAE acoustic space of a TTS system
Penny Karanasou, Sri Karlapati, Alexis Moinet +5
Many factors influence speech yielding different renditions of a given sentence. Generative models, such as variational autoencoders (VAEs), capture this variability and allow mult…
Prosodic Representation Learning and Contextual Sampling for Neural Text-to-Speech
Sri Karlapati, Ammar Abbas, Zack Hodari +4
In this paper, we introduce Kathaka, a model trained with a novel two-stage training process for neural speech synthesis with contextually appropriate prosody. In Stage I, we learn…
CAMP: a Two-Stage Approach to Modelling Prosody in Context
Zack Hodari, Alexis Moinet, Sri Karlapati +6
Prosody is an integral part of communication, but remains an open problem in state-of-the-art speech synthesis. There are two major issues faced when modelling prosody: (1) prosody…