← Back to all news
arXiv Machine Learning By Aman Tiwari, Akshay Kalkunte, Akintunde Oladipo, Jash Shah, Tara Bogavelli, Hoang Nguyen, Nishanth Madhusudhan, Vishal Juneja, Sridhar Nemala, Srinivas Sunkara, Sathwik Tejaswi Madhusudhan, Shruthan Radhakrishna, Masoud Hashemi, Kelechi Ogueji, Khalil Slimi, Saloni Mittal, Pulkit Pattnaik, Shashank Maiya, Dhruv Jhamb, Esakkivel Esakkiraja, Katrina Stankiewicz, Gabrielle Gauthier Melan\c{c}on, Fanny Riols, Amit Saha, Lakshmi Sirisha Chodisetty, Nitin Aggarwal, Anil Madamala, Sagar Davasam, Segan Subramanian, Vikas Yadav, Sai Rajeswar Mudumba

Apriel Voice 27B Preview: An Open Model for Speech, Reasoning, and Tool Use

Read the original on arXiv Machine Learning →

Apriel Voice 27B Preview is an open speech‑language model that unifies speech recognition, contextual reasoning, conversation maintenance, and tool use within a single reasoning backbone. Built on the post‑trained Gemma 4 26B‑A4B checkpoint, it processes speech directly and generates responses and tool calls without a separate dialogue model, using a two‑stage training procedure that adapts the projector and backbone through supervised fine‑tuning, text replay, and cross‑entropy/KL supervision. The model achieves strong performance on benchmarks such as Big Bench Audio (98.90), Speech‑BFCL (81.13), and τ‑Voice (65.51% task success), with a mean latency of 1.91 s, and is deployed on a custom serving platform for interactive voice interactions.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Computation and Language
Sep 11

RetroThinker: Enabling Retrospective Thinking in Speech LLMs

RetroThinker is a multi-stage post‑training framework that enhances SpeechLLMs by enabling them to self‑verify and forward‑correct Chain‑of‑Thought reasoning steps during inference. It combines supervised fine‑tuning on curated retrospective thinking data with length‑based direct preference optimization to improve reasoning while the user speaks. On the GSM8K benchmark, RetroThinker achieves an 11% absolute accuracy gain over non‑retrospective baselines while maintaining comparable latency.

By Yi-Jen Shih, Puyuan Peng, Abdelrahman Mohamed, David Harwath
llmsreinforcement-learningfine-tuningmultimodalbenchmarks
More like this →
arXiv Computation and Language
Sep 18

A frontend-backend architecture for tool calls in full-duplex speech models

The paper introduces a frontend‑backend architecture for full‑duplex speech‑to‑speech models that enables tool calls while preserving natural conversational flow. The frontend emits a delegation token and streams ASR transcripts to a text‑based backend LLM, which performs tool calls and returns results that are re‑injected into the frontend via a lightweight prefill‑and‑repeat mechanism before streaming TTS synthesis. In single‑turn evaluations the system achieves 92‑97% tool‑call recall, 81.2% accuracy in rejecting irrelevant calls, and competitive performance on Full‑Duplex‑Bench‑V3 and EVA‑Bench when paired with a large backend model.

By Ke Hu, Slyne Deng, Chen Chen, Elena Rastorgueva, Edresson Casanova, Punit Kumar, Dharmendra Choudhary, Nikhil Srihari, Ameya Sunil Mahabaleshwarkar, Viet Anh Trinh, Slim Essid, Oluwatobi Olabiyi, Zhehuai Chen
llmsagentsmultimodal
More like this →