In this talk I will describe our recent efforts within the PT-STAR project for speech translation across languages. I will begin with brief descriptions about the component systems for speech recognition, machine translation and speech synthesis and talk in greater detail about modeling and conversion of prosodic aspects of speech across languages, a major part of speaking style. Illustrating with example demos for the case of English<->Portuguese translation, I will comment on the bottlenecks in the current speech translation technology and list some challenges for the future that may be of interest to ML/Speech/NLP research community.
Speech Translation: Modeling and Conversion of speaking style across languages
March 12, 2013
1:00 pm
Gopala Krishna Anumanchipalli
Gopala is a PhD candidate in the CMU|Portugal program jointly advised by Prof. Alan Black at LTI/CMU and Prof. Luis Oliveira at INESC-ID/IST. His interests are in all aspects of speech and language processing and his PhD thesis is in prosody modeling for speech synthesis and voice conversion within and across languages. He holds a Bachelors in Engineering (CS/AI) and Masters in science (CS) both from IIIT-Hyderabad, India.LTI, CMU and L2F, INESC-IDSeminários
Últimos seminários
Cost-Sensitive Learning to Defer to Multiple Experts
March 2, 2026Large language models (LLMs) have emerged as strong contenders in machine translation. Yet, they often fall behind specialized neural machine…
Fair Federated Learning under Group-Specific Distributed Concept Drift
February 24, 2026Machine learning models can become unfair when different groups experience changes in data over time, a phenomenon called group-specific concept…
Unlocking Latent Discourse Translation in LLMs Through Quality-Aware Decoding
June 17, 2025Large language models (LLMs) have emerged as strong contenders in machine translation. Yet, they often fall behind specialized neural machine…
Speech as a Biomarker for Disease Detection
May 20, 2025Today’s overburdened health systems face numerous challenges, exacerbated by an aging population. Speech emerges as a ubiquitous biomarker with strong…
