Cover Image

Benchmarking Training Paradigms, Dataset Composition, and Model Scaling for Child ASR in ESPnet

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ying, Anyu, Shankar, Natarajan Balaji, Lin, Chyi-Jiunn, Shi, Mohan, Wang, Pu, Shim, Hye-jin, Arora, Siddhant, Van hamme, Hugo, Alwan, Abeer, Watanabe, Shinji
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

CHSER: A Dataset and Case Study on Generative Speech Error Correction for Child ASR
by: Shankar, Natarajan Balaji, et al.
Published: (2025)

Comparing Unsupervised and Supervised Semantic Speech Tokens: A Case Study of Child ASR
by: Shi, Mohan, et al.
Published: (2025)

Selective Attention Merging for low resource tasks: A case study of Child ASR
by: Shankar, Natarajan Balaji, et al.
Published: (2025)

Benchmarking Children's ASR with Supervised and Self-supervised Speech Foundation Models
by: Fan, Ruchao, et al.
Published: (2024)

SOA: Reducing Domain Mismatch in SSL Pipeline by Speech Only Adaptation for Low Resource ASR
by: Shankar, Natarajan Balaji, et al.
Published: (2024)

Mind the Shift: Using Delta SSL Embeddings to Enhance Child ASR
by: Wang, Zilai, et al.
Published: (2026)

UniEnc-CASSNAT: An Encoder-only Non-autoregressive ASR for Speech SSL Models
by: Fan, Ruchao, et al.
Published: (2024)

SSVD: Structured SVD for Parameter-Efficient Fine-Tuning and Benchmarking under Domain Shift in ASR
by: Wang, Pu, et al.
Published: (2025)

ESPnet-EZ: Python-only ESPnet for Easy Fine-tuning and Integration
by: Someki, Masao, et al.
Published: (2024)

An Age-Agnostic System for Robust Speaker Verification
by: Zheng, Jiusi, et al.
Published: (2025)

Unifying Diarization, Separation, and ASR with Multi-Speaker Encoder
by: Shakeel, Muhammad, et al.
Published: (2025)

CALM: Joint Contextual Acoustic-Linguistic Modeling for Personalization of Multi-Speaker ASR
by: Shakeel, Muhammad, et al.
Published: (2026)

STACodec: Semantic Token Assignment for Balancing Acoustic Fidelity and Semantic Information in Audio Codecs
by: Zhang, Kaiyuan, et al.
Published: (2026)

Addressing Bias in Spoken Language Systems Used in the Development and Implementation of Automated Child Language‐Based Assessment
by: Alison L. Bailey, et al.
Published: (2025)

SSVD-O: Parameter-Efficient Fine-Tuning with Structured SVD for Speech Recognition
by: Wang, Pu, et al.
Published: (2026)

Semi-Autoregressive Streaming ASR With Label Context
by: Arora, Siddhant, et al.
Published: (2023)

Geolocation-Aware Robust Spoken Language Identification
by: Wang, Qingzheng, et al.
Published: (2025)

ESPnet-SDS: Unified Toolkit and Demo for Spoken Dialogue Systems
by: Arora, Siddhant, et al.
Published: (2025)

Muskits-ESPnet: A Comprehensive Toolkit for Singing Voice Synthesis in New Paradigm
by: Wu, Yuning, et al.
Published: (2024)

ARECHO: Autoregressive Evaluation via Chain-Based Hypothesis Optimization for Speech Multi-Metric Estimation
by: Shi, Jiatong, et al.
Published: (2025)

ESPnet-SpeechLM: An Open Speech Language Model Toolkit
by: Tian, Jinchuan, et al.
Published: (2025)

Beyond Silence: Bias Analysis through Loss and Asymmetric Approach in Audio Anti-Spoofing
by: Shim, Hye-jin, et al.
Published: (2024)

Inverse-Hessian Regularization for Continual Learning in ASR
by: Eeckt, Steven Vander, et al.
Published: (2026)

Efficient Rehearsal for Continual Learning in ASR via Singular Value Tuning
by: Eeckt, Steven Vander, et al.
Published: (2026)

DYNAC: Dynamic Vocabulary based Non-Autoregressive Contextualization for Speech Recognition
by: Sudo, Yui, et al.
Published: (2025)

Uni-VERSA: Versatile Speech Assessment with a Unified Network
by: Shi, Jiatong, et al.
Published: (2025)

Disentangled-Transformer: An Explainable End-to-End Automatic Speech Recognition Model with Speech Content-Context Separation
by: Wang, Pu, et al.
Published: (2024)

OpenBEATs: A Fully Open-Source General-Purpose Audio Encoder
by: Bharadwaj, Shikhar, et al.
Published: (2025)

The CMU-AIST submission for the ICME 2025 Audio Encoder Challenge
by: Bharadwaj, Shikhar, et al.
Published: (2026)

OWSM v4: Improving Open Whisper-Style Speech Models via Data Scaling and Cleaning
by: Peng, Yifan, et al.
Published: (2025)

To what extent can ASV systems naturally defend against spoofing attacks?
by: Jung, Jee-weon, et al.
Published: (2024)

Spiralformer: Low Latency Encoder for Streaming Speech Recognition with Circular Layer Skipping and Early Exiting
by: Tsunoo, Emiru, et al.
Published: (2025)

Finding Task-specific Subnetworks in Multi-task Spoken Language Understanding Model
by: Futami, Hayato, et al.
Published: (2024)

Rapid Language Adaptation for Multilingual E2E Speech Recognition Using Encoder Prompting
by: Kashiwagi, Yosuke, et al.
Published: (2024)

Decoder-only Architecture for Speech Recognition with CTC Prompts and Text Data Augmentation
by: Tsunoo, Emiru, et al.
Published: (2023)

Hypothesis Clustering and Merging: Novel MultiTalker Speech Recognition with Speaker Tokens
by: Kashiwagi, Yosuke, et al.
Published: (2024)

Decoder-only Architecture for Streaming End-to-end Speech Recognition
by: Tsunoo, Emiru, et al.
Published: (2024)

Talking Turns: Benchmarking Audio Foundation Models on Turn-Taking Dynamics
by: Arora, Siddhant, et al.
Published: (2025)

GLoRIA: Gated Low-Rank Interpretable Adaptation for Dialectal ASR
by: Mehralian, Pouya, et al.
Published: (2026)

G-IFT: A Gated Linear Unit adapter with Iterative Fine-Tuning for Low-Resource Children's Speaker Verification
by: Shetty, Vishwas M., et al.
Published: (2025)