Voice conversion boosts speech recognition in banking call centers
Enhancing Speech Recognition through Text-to-Speech and Voice Conversion Augmentation
Sound
Summary
Getting enough real audio to train speech recognition systems is hard, so synthetic speech is used instead. The authors studied different ways to create synthetic speech, including making new voices and changing existing ones, especially for banking call centers. They found that advanced voice conversion methods made the synthetic speech sound better and helped the speech recognition work more accurately. Their work shows how these techniques can improve speech recognition in specific industries.
What this means in practice
- •For call center software teams: Improve speech recognition accuracy for customer service calls by using voice conversion augmented data tailored for call center banking contexts.
- •For voice assistant developers: Enhance voice assistants’ understanding in banking and financial services by augmenting training data with realistic synthetic voices generated via Seed-VC.
Authors
Yunus Emre Ozkose, Ali Haznedaroglu
Abstract
Given the challenges associated with obtaining large volumes of real-world audio, the advancement of Automatic Speech Recognition (ASR) systems increasingly depends on synthetic data. This study focuses on the call center-banking domain, providing a targeted analysis of ASR models in this context. We evaluate real and synthetic datasets, using Word Error Rate (WER) and Character Error Rate (CER) as metrics, and employ a speech quality model to assess the impact on ASR performance. Our research compares Text-to-Speech (TTS) and advanced voice conversion methods, including KNNVC, Seed-VC, and Vec2Wav2, revealing significant improvements in speech quality and ASR accuracy, particularly with Seed-VC. Additionally, our domain-specific experimentation provides insight into the unique challenges and opportunities that arise when applying ASR technologies to industry-relevant settings. This highlights the potential of voice conversion technologies to enhance ASR systems, guiding future research in diverse linguistic scenarios, and paving the way for the broader application of ASR innovations across various fields.