Copertina

Aligner-Encoders: Self-Attention Transformers Can Be Self-Transducers

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Stooke, Adam, Prabhavalkar, Rohit, Sim, Khe Chai, Mengibar, Pedro Moreno
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Sound Artificial Intelligence Machine Learning Audio and Speech Processing
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Hierarchical Recurrent Adapters for Efficient Multi-Task Adaptation of Large Speech Models
di: Munkhdalai, Tsendsuren, et al.
Pubblicazione: (2024)

Extreme Encoder Output Frame Rate Reduction: Improving Computational Latencies of Large End-to-End Models
di: Prabhavalkar, Rohit, et al.
Pubblicazione: (2024)

Aligner-Guided Training Paradigm: Advancing Text-to-Speech Models with Aligner Guided Duration
di: Lou, Haowei, et al.
Pubblicazione: (2024)

SSPS: Self-Supervised Positive Sampling for Robust Self-Supervised Speaker Verification
di: Lepage, Theo, et al.
Pubblicazione: (2025)

Piano Transcription by Hierarchical Language Modeling with Pretrained Roll-based Encoders
di: Li, Dichucheng, et al.
Pubblicazione: (2025)

Scaling Self-Supervised Representation Learning for Symbolic Piano Performance
di: Bradshaw, Louis, et al.
Pubblicazione: (2025)

SSLAM: Enhancing Self-Supervised Models with Audio Mixtures for Polyphonic Soundscapes
di: Alex, Tony, et al.
Pubblicazione: (2025)

Translation-Equivariant Self-Supervised Learning for Pitch Estimation with Optimal Transport
di: Torres, Bernardo, et al.
Pubblicazione: (2025)

Self-Supervised Disentangled Representation Learning for Robust Target Speech Extraction
di: Mu, Zhaoxi, et al.
Pubblicazione: (2023)

PESTO: Real-Time Pitch Estimation with Self-supervised Transposition-equivariant Objective
di: Riou, Alain, et al.
Pubblicazione: (2025)

DAISY: Data Adaptive Self-Supervised Early Exit for Speech Representation Models
di: Lin, Tzu-Quan, et al.
Pubblicazione: (2024)

Self-Supervised Speech Quality Estimation and Enhancement Using Only Clean Speech
di: Fu, Szu-Wei, et al.
Pubblicazione: (2024)

Label-Looping: Highly Efficient Decoding for Transducers
di: Bataev, Vladimir, et al.
Pubblicazione: (2024)

DiceHuBERT: Distilling HuBERT with a Self-Supervised Learning Objective
di: Chi, Hyung Gun, et al.
Pubblicazione: (2025)

Soft Clustering Anchors for Self-Supervised Speech Representation Learning in Joint Embedding Prediction Architectures
di: Ioannides, Georgios, et al.
Pubblicazione: (2026)

AnyEnhance: A Unified Generative Model with Prompt-Guidance and Self-Critic for Voice Enhancement
di: Zhang, Junan, et al.
Pubblicazione: (2025)

DARNet: Dual Attention Refinement Network with Spatiotemporal Construction for Auditory Attention Detection
di: Yan, Sheng, et al.
Pubblicazione: (2024)

RNN-Transducer-based Losses for Speech Recognition on Noisy Targets
di: Bataev, Vladimir
Pubblicazione: (2025)

EAT: Self-Supervised Pre-Training with Efficient Audio Transformer
di: Chen, Wenxi, et al.
Pubblicazione: (2024)

Speaker Emotion Recognition: Leveraging Self-Supervised Models for Feature Extraction Using Wav2Vec2 and HuBERT
di: Jafarzadeh, Pourya, et al.
Pubblicazione: (2024)

SelfVC: Voice Conversion With Iterative Refinement using Self Transformations
di: Neekhara, Paarth, et al.
Pubblicazione: (2023)

Pushing the Limits of Beam Search Decoding for Transducer-based ASR models
di: Grigoryan, Lilit, et al.
Pubblicazione: (2025)

Cross-Attention with Confidence Weighting for Multi-Channel Audio Alignment
di: Nihal, Ragib Amin, et al.
Pubblicazione: (2025)

Model as Loss: A Self-Consistent Training Paradigm
di: Phaye, Saisamarth Rajesh, et al.
Pubblicazione: (2025)

Fast Context-Biasing for CTC and Transducer ASR models with CTC-based Word Spotter
di: Andrusenko, Andrei, et al.
Pubblicazione: (2024)

JEPA as a Neural Tokenizer: Learning Robust Speech Representations with Density Adaptive Attention
di: Ioannides, Georgios, et al.
Pubblicazione: (2025)

Enhanced Speech Emotion Recognition with Efficient Channel Attention Guided Deep CNN-BiLSTM Framework
di: Kundu, Niloy Kumar, et al.
Pubblicazione: (2024)

Whisfusion: Parallel ASR Decoding via a Diffusion Transformer
di: Kwon, Taeyoun, et al.
Pubblicazione: (2025)

Multi-blank Transducers for Speech Recognition
di: Xu, Hainan, et al.
Pubblicazione: (2022)

Generating Music with Structure Using Self-Similarity as Attention
di: Hager, Sophia, et al.
Pubblicazione: (2024)

Masked Audio Generation using a Single Non-Autoregressive Transformer
di: Ziv, Alon, et al.
Pubblicazione: (2024)

DeepGB-TB: A Risk-Balanced Cross-Attention Gradient-Boosted Convolutional Network for Rapid, Interpretable Tuberculosis Screening
di: Lu, Zhixiang, et al.
Pubblicazione: (2025)

DOA-Aware Audio-Visual Self-Supervised Learning for Sound Event Localization and Detection
di: Fujita, Yoto, et al.
Pubblicazione: (2024)

Lightweight Self-Supervised Detection of Fundamental Frequency and Accurate Probability of Voicing in Monophonic Music
di: Bitra, Venkat Suprabath, et al.
Pubblicazione: (2026)

Multimodal Audio-based Disease Prediction with Transformer-based Hierarchical Fusion Network
di: Cai, Jinjin, et al.
Pubblicazione: (2024)

MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer
di: Wang, Yuancheng, et al.
Pubblicazione: (2024)

Whisper in Medusa's Ear: Multi-head Efficient Decoding for Transformer-based ASR
di: Segal-Feldman, Yael, et al.
Pubblicazione: (2024)

Do we really need Self-Attention for Streaming Automatic Speech Recognition?
di: Dkhissi, Youness, et al.
Pubblicazione: (2026)

Temporal-Channel Modeling in Multi-head Self-Attention for Synthetic Speech Detection
di: Truong, Duc-Tuan, et al.
Pubblicazione: (2024)

Comparative Analysis of CNN and Transformer Architectures with Heart Cycle Normalization for Automated Phonocardiogram Classification
di: Sondermann, Martin, et al.
Pubblicazione: (2025)