Scalable Multilingual Frontend for TTS
This paper describes progress towards making a Neural Text-to-Speech (TTS) Frontend that works for many languages and can be easily extended to new languages. We take a Machine Translation (MT) inspired approach to constructing the frontend, and model both text normalization and pronunciation on a sentence level by building and using sequence-to-sequence (S2S) models. We experimented with training normalization and pronunciation as separate S2S models and with training a single S2S model combining both functions. For our language-independent approach to pronunciation we do not use a lexicon. Instead all pronunciations, including context-based pronunciations, are captured in the S2S model. We also present a language-independent chunking and splicing technique that allows us to process arbitrary-length sentences. Models for 18 languages were trained and evaluated. Many of the accuracy measurements are above 99%. We also evaluated the models in the context of end-to-end synthesis against our current production system.
Code (0)
등록된 구현이 없습니다.
Tasks
ChunkingMachine TranslationSentenceText Normalizationtext-to-speechText to SpeechTranslationSimilar Papers 제목 키워드 기반
FrontendBench: A Benchmark for Evaluating LLMs on Front-End Development via Automatic Evaluation
Large Language Models (LLMs) have made significant strides in front-end code generation. However, existing benchmarks exhibit several critical limitations: many tasks are overly simplistic, test cases often lack rigor, a…
Code GenerationAutomated Classification of Cybercrime Complaints using Transformer-based Language Models for Hinglish Texts
The rise in cybercrime and the complexity of multilingual and code-mixed complaints present significant challenges for law enforcement and cybersecurity agencies. These organizations need automated, scalable methods to i…
Data AugmentationMultilingual Dataset Integration Strategies for Robust Audio Deepfake Detection: A SAFE Challenge System
The SAFE Challenge evaluates synthetic speech detection across three tasks: unmodified audio, processed audio with compression artifacts, and laundered audio designed to evade detection. We systematically explore self-su…
Self-Supervised LearningAudio Deepfake DetectionSpeech Separation with Pretrained Frontend to Minimize Domain Mismatch
Speech separation seeks to separate individual speech signals from a speech mixture. Typically, most separation models are trained on synthetic data due to the unavailability of target reference in real-world cocktail pa…
Speech SeparationLearnable Acoustic Frontends in Bird Activity Detection
Autonomous recording units and passive acoustic monitoring present minimally intrusive methods of collecting bioacoustics data. Combining this data with species agnostic bird activity detection systems enables the monito…
Action DetectionActivity DetectionBird Audio Detection