7 papers
mu-bench: A Multilingual Utterance Transcription Benchmark
Andrea Li, Soham Ray
Voice agents depend on accurate automatic speech recognition (ASR) to act on what callers say, yet ASR is evaluated on read, English-centric speech with word error rate (WER), whic…
-Multilingual: Benchmarking Voice Agents Across Languages
Soham Ray, Edgard dos Santos Paiva, Ruben Valenzuela +3
English-only benchmarks expose only a narrow slice of voice-agent behavior. We introduce -Multilingual, extending -Voice to Spanish, Brazilian Portuguese, Hindi, Korean, and…
-Elicitation: Benchmarking multi-turn entity extraction in voice agents
Soham Ray, Victor Barres
Voice agents often need to collect names, addresses, identifiers, dates, and times exactly, yet end-to-end benchmarks obscure where capture fails. We introduce -Elicitation, a 2…
-Voice: Benchmarking Full-Duplex Voice Agents on Real-World Domains
Soham Ray, Keshav Dhandhania, Victor Barres +1
Full-duplex voice agents--systems that listen and speak simultaneously--are rapidly moving from research to production. However, existing evaluations address conversational dynamic…
Symmetry and Topology in a Non-Hermitian Kitaev chain
Ayush Raj, Soham Ray, Sai Satyam Samal
We investigate the non-Hermitian Kitaev chain with non-reciprocal hopping amplitudes and asymmetric superconducting pairing. We work out the symmetry structure of the model and sho…
-Bench: Evaluating Conversational Agents in a Dual-Control Environment
Victor Barres, Honghua Dong, Soham Ray +2
Existing benchmarks for conversational AI agents simulate single-control environments, where only the AI agent can use tools to interact with the world, while the user remains a pa…
Sample-Efficient Diffusion for Text-To-Speech Synthesis
Justin Lovelace, Soham Ray, Kwangyoun Kim +2
This work introduces Sample-Efficient Speech Diffusion (SESD), an algorithm for effective speech synthesis in modest data regimes through latent diffusion. It is based on a novel d…