Cover Image

FLToP CTC: Frame-Level Token Pruning via Relative Threshold for Efficient and Memory-Saving Decoding on Diverse Platforms

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shree, Atul, Jupuru, Harshith
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Sound Audio and Speech Processing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

CTC Blank Triggered Dynamic Layer-Skipping for Efficient CTC-based Speech Recognition
by: Hou, Junfeng, et al.
Published: (2024)

kNN-CTC: Enhancing ASR via Retrieval of CTC Pseudo Labels
by: Zhou, Jiaming, et al.
Published: (2023)

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

Guiding Frame-Level CTC Alignments Using Self-knowledge Distillation
by: Kim, Eungbeom, et al.
Published: (2024)

Joint Beam Search Integrating CTC, Attention, and Transducer Decoders
by: Sudo, Yui, et al.
Published: (2024)

Token Pruning in Audio Transformers: Optimizing Performance and Decoding Patch Importance
by: Lee, Taehan, et al.
Published: (2025)

NTC-KWS: Noise-aware CTC for Robust Keyword Spotting
by: Xi, Yu, et al.
Published: (2024)

Say More with Less: Variable-Frame-Rate Speech Tokenization via Adaptive Clustering and Implicit Duration Coding
by: Zheng, Rui-Chen, et al.
Published: (2025)

CR-CTC: Consistency regularization on CTC for improved speech recognition
by: Yao, Zengwei, et al.
Published: (2024)

MFA-KWS: Effective Keyword Spotting with Multi-head Frame-asynchronous Decoding
by: Xi, Yu, et al.
Published: (2025)

Decoding Strategies for Diffusion-Based ASR: A Systematic Evaluation of Confidence-Based Thresholding
by: Yeo, Jeong Hun, et al.
Published: (2026)

CJST: CTC Compressor based Joint Speech and Text Training for Decoder-Only ASR
by: Zhou, Wei, et al.
Published: (2024)

Delayed-KD: Delayed Knowledge Distillation based CTC for Low-Latency Streaming ASR
by: Li, Longhao, et al.
Published: (2025)

Data-Efficient Low-Complexity Acoustic Scene Classification via Distilling and Progressive Pruning
by: Han, Bing, et al.
Published: (2024)

SegAug: CTC-Aligned Segmented Augmentation For Robust RNN-Transducer Based Speech Recognition
by: Le, Khanh, et al.
Published: (2025)

CTC-TTS: LLM-based dual-streaming text-to-speech with CTC alignment
by: Liu, Hanwen, et al.
Published: (2026)

Few-Shot Bioacoustic Event Detection with Frame-Level Embedding Learning System
by: Zhao, PengYuan, et al.
Published: (2024)

SPADE: Structured Pruning and Adaptive Distillation for Efficient LLM-TTS
by: Nguyen, Tan Dat, et al.
Published: (2025)

HD-PPT: Hierarchical Decoding of Content- and Prompt-Preference Tokens for Instruction-based TTS
by: Nie, Sihang, et al.
Published: (2025)

Speaker-Distinguishable CTC: Learning Speaker Distinction Using CTC for Multi-Talker Speech Recognition
by: Sakuma, Asahi, et al.
Published: (2025)

StreamFlow: Streaming Flow Matching with Block-wise Guided Attention Mask for Speech Token Decoding
by: Guo, Dake, et al.
Published: (2025)

When Voice Matters: Evidence of Gender Disparity in Positional Bias of SpeechLLMs
by: Satish, Shree Harsha Bokkahalli, et al.
Published: (2025)

Addressing Index Collapse of Large-Codebook Speech Tokenizer with Dual-Decoding Product-Quantized Variational Auto-Encoder
by: Guo, Haohan, et al.
Published: (2024)

Unimodal Aggregation for CTC-based Speech Recognition
by: Fang, Ying, et al.
Published: (2023)

Token-Level Logits Matter: A Closer Look at Speech Foundation Models for Ambiguous Emotion Recognition
by: Halim, Jule Valendo, et al.
Published: (2025)

Accelerating Flow-Matching-Based Text-to-Speech via Empirically Pruned Step Sampling
by: Zheng, Qixi, et al.
Published: (2025)

Phone-Level Prosody Modelling with GMM-Based MDN for Diverse and Controllable Speech Synthesis
by: Du, Chenpeng, et al.
Published: (2021)

EfficientASR: Speech Recognition Network Compression via Attention Redundancy and Chunk-Level FFN Optimization
by: Wang, Jianzong, et al.
Published: (2024)

Analyzing the Importance of Blank for CTC-Based Knowledge Distillation
by: Hilmes, Benedikt, et al.
Published: (2025)

Efficient Audio Captioning with Encoder-Level Knowledge Distillation
by: Xu, Xuenan, et al.
Published: (2024)

FlexCTC: GPU-powered CTC Beam Decoding With Advanced Contextual Abilities
by: Grigoryan, Lilit, et al.
Published: (2025)

CodecSlime: Temporal Redundancy Compression of Neural Speech Codec via Dynamic Frame Rate
by: Wang, Hankun, et al.
Published: (2025)

Enhancing CTC-based speech recognition with diverse modeling units
by: Han, Shiyi, et al.
Published: (2024)

Adapting Whisper for Streaming Speech Recognition via Two-Pass Decoding
by: Zhou, Haoran, et al.
Published: (2025)

SepPrune: Structured Pruning for Efficient Deep Speech Separation
by: Li, Yuqi, et al.
Published: (2025)

FLAM: Frame-Wise Language-Audio Modeling
by: Wu, Yusong, et al.
Published: (2025)

MOSS-Audio-Tokenizer: Scaling Audio Tokenizers for Future Audio Foundation Models
by: Gong, Yitian, et al.
Published: (2026)

Lightweight Transducer Based on Frame-Level Criterion
by: Wan, Genshun, et al.
Published: (2024)

LegoSLM: Connecting LLM with Speech Encoder using CTC Posteriors
by: Ma, Rao, et al.
Published: (2025)

Disentangling Speakers in Multi-Talker Speech Recognition with Speaker-Aware CTC
by: Kang, Jiawen, et al.
Published: (2024)