Cover Image

Splitformer: An improved early-exit architecture for automatic speech recognition on edge devices

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lasbordes, Maxence, Falavigna, Daniele, Brutti, Alessio
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Sound Audio and Speech Processing 68T50 (Primary) I.2.7; I.5.4
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition
by: Hori, Takaaki, et al.
Published: (2025)

Quantifying the effect of speech pathology on automatic and human speaker verification
by: Halpern, Bence Mark, et al.
Published: (2024)

Quantization for OpenAI's Whisper Models: A Comparative Analysis
by: Andreyev, Allison
Published: (2025)

A Unified Model For Voice and Accent Conversion In Speech and Singing using Self-Supervised Learning and Feature Extraction
by: Cheripally, Sowmya
Published: (2024)

Thaka at KSAA-2026 Task 2: Regularized Fine-Tuning for Arabic Speech Diacritization
by: Alamr, Meshal, et al.
Published: (2026)

Predicting Upcoming Stuttering Events from Three-Second Audio: Stratified Evaluation Reveals Severity-Selective Precursors, and the Model Deploys Fully On-Device
by: Kozak, Nazar
Published: (2026)

Developing Acoustic Models for Automatic Speech Recognition in Swedish
by: Salvi, Giampiero
Published: (2024)

Emotional Voice Messages (EMOVOME) database: emotion recognition in spontaneous voice messages
by: Zaragozá, Lucía Gómez, et al.
Published: (2024)

Investigating Prosodic Signatures via Speech Pre-Trained Models for Audio Deepfake Source Attribution
by: Phukan, Orchid Chetia, et al.
Published: (2024)

Strong Alone, Stronger Together: Synergizing Modality-Binding Foundation Models with Optimal Transport for Non-Verbal Emotion Recognition
by: Phukan, Orchid Chetia, et al.
Published: (2024)

Multi-View Multi-Task Modeling with Speech Foundation Models for Speech Forensic Tasks
by: Phukan, Orchid Chetia, et al.
Published: (2024)

Avengers Assemble: Amalgamation of Non-Semantic Features for Depression Detection
by: Phukan, Orchid Chetia, et al.
Published: (2024)

SeQuiFi: Mitigating Catastrophic Forgetting in Speech Emotion Recognition with Sequential Class-Finetuning
by: Jain, Sarthak, et al.
Published: (2024)

Representation Loss Minimization with Randomized Selection Strategy for Efficient Environmental Fake Audio Detection
by: Phukan, Orchid Chetia, et al.
Published: (2024)

ParaNoise-SV: Integrated Approach for Noise-Robust Speaker Verification with Parallel Joint Learning of Speech Enhancement and Noise Extraction
by: Kim, Minu, et al.
Published: (2025)

Rethinking the Multilingual Reasoning Gap with Layer Swap
by: Lasbordes, Maxence, et al.
Published: (2026)

Training dynamic models using early exits for automatic speech recognition on resource-constrained devices
by: Wright, George August, et al.
Published: (2023)

From Black Box to Glass Box: Cross-Model ASR Disagreement to Prioto Review in Ambient AI Scribe Documentation
by: Karbalaie, Abdolamir, et al.
Published: (2026)

An End-to-End Approach for Korean Wakeword Systems with Speaker Authentication
by: Seo, Geonwoo
Published: (2025)

Prevailing Research Areas for Music AI in the Era of Foundation Models
by: Wei, Megan, et al.
Published: (2024)

Are Music Foundation Models Better at Singing Voice Deepfake Detection? Far-Better Fuse them with Speech Foundation Models
by: Phukan, Orchid Chetia, et al.
Published: (2024)

AI-based Drone Assisted Human Rescue in Disaster Environments: Challenges and Opportunities
by: Papyan, Narek, et al.
Published: (2024)

SpeechAccentLLM: A Unified Framework for Foreign Accent Conversion and Text to Speech
by: Cheng, Zhuangfei, et al.
Published: (2025)

AURA: Agent for Understanding, Reasoning, and Automated Tool Use in Voice-Driven Tasks
by: Maben, Leander Melroy, et al.
Published: (2025)

MENASpeechBank: A Reference Voice Bank with Persona-Conditioned Multi-Turn Conversations for AudioLLMs
by: Ali, Zien Sheikh, et al.
Published: (2026)

Multi-Task Instruction Tuning via Data Scheduling for Low-Resource Arabic AudioLLMs
by: Bhatti, Hunzalah Hassan, et al.
Published: (2026)

SeamlessEdit: Background Noise Aware Zero-Shot Speech Editing with in-Context Enhancement
by: Chen, Kuan-Yu, et al.
Published: (2025)

NAAQA: A Neural Architecture for Acoustic Question Answering
by: Abdelnour, Jerome, et al.
Published: (2021)

Deep Feed-Forward Neural Network for Bangla Isolated Speech Recognition
by: Bhadra, Dipayan, et al.
Published: (2025)

Graph Connectionist Temporal Classification for Phoneme Recognition
by: Grafé, Henry, et al.
Published: (2025)

Multilingual Multi-Label Emotion Classification at Scale with Synthetic Data
by: Borisov, Vadim
Published: (2026)

Improving Cross-Lingual Phonetic Representation of Low-Resource Languages Through Language Similarity Analysis
by: Kim, Minu, et al.
Published: (2025)

Should you use a probabilistic duration model in TTS? Probably! Especially for spontaneous speech
by: Mehta, Shivam, et al.
Published: (2024)

STOPA: A Database of Systematic VariaTion Of DeePfake Audio for Open-Set Source Tracing and Attribution
by: Firc, Anton, et al.
Published: (2025)

Segment Boundary Detection via Class Entropy Measurements in Connectionist Phoneme Recognition
by: Salvi, Giampiero
Published: (2024)

Impact of Frame Rates on Speech Tokenizer: A Case Study on Mandarin and English
by: Zhang, Haoyang, et al.
Published: (2025)

STRUM: A Spectral Transcription and Rhythm Understanding Model for End-to-End Generation of Playable Rhythm-Game Charts
by: Opria, Joshua
Published: (2026)

Impact of Phonetics on Speaker Identity in Adversarial Voice Attack
by: Dar, Daniyal Kabir, et al.
Published: (2025)

An accurate and revised version of optical character recognition-based speech synthesis using LabVIEW
by: Mehta, Prateek, et al.
Published: (2025)

Beyond Deep Learning: Speech Segmentation and Phone Classification with Neural Assemblies
by: Adelson, Trevor, et al.
Published: (2026)