Sequence Transduction with Recurrent Neural Networks

Many machine learning tasks can be expressed as the transformation---or \emph{transduction}---of input sequences into output sequences: speech recognition, machine translation, protein secondary structure prediction and text-to-speech to name but a few. One of the key challenges in sequence transduction is learning to represent both the input and output sequences in a way that is invariant to sequential distortions such as shrinking, stretching and translating. Recurrent neural networks (RNNs) are a powerful sequence learning architecture that has proven capable of learning such representations. However RNNs traditionally require a pre-defined alignment between the input and output sequences to perform transduction. This is a severe limitation since \emph{finding} the alignment is the most difficult aspect of many sequence transduction problems. Indeed, even determining the length of the output sequence is often challenging. This paper introduces an end-to-end, probabilistic sequence transduction system, based entirely on RNNs, that is in principle able to transform any input sequence into any finite, discrete output sequence. Experimental results for phoneme recognition are provided on the TIMIT speech corpus.

• Publication year

  2012

• Venue

  arXiv.org

• Publication date

  2012-11-14

• Fields of study

  Mathematics, Computer Science

• Identifiers
  arXiv 1211.3711
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Generating Text with Recurrent Neural Networks

  2011cited by this paper
• Phone Recognition with the Mean-Covariance Restricted Boltzmann Machine

  2010influential reference
• Recurrent neural network based language model

  2010cited by this paper
• Offline Handwriting Recognition with Multidimensional Recurrent Neural Networks

  2008cited by this paper
• Unconstrained On-line Handwriting Recognition with Recurrent Neural Networks

  2007cited by this paper
• Unconstrained Online Handwriting Recognition with Recurrent Neural Networks

  2007cited by this paper
• Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks

  2006influential reference
• Rejection strategies for offline handwritten text line recognition

  2006cited by this paper
• 2005 Special Issue: Framewise phoneme classification with bidirectional LSTM and other neural network architectures

  2005cited by this paper
• Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data

  2001cited by this paper
• Gradient Flow in Recurrent Nets: the Difficulty of Learning Long-Term Dependencies

  2001cited by this paper
• Long short-term memory in recurrent neural networks

  2001cited by this paper
• Gradient-based learning applied to document recognition

  1998cited by this paper
• Global training of document processing systems using graph transformer networks

  1997cited by this paper
• Bidirectional recurrent neural networks

  1997cited by this paper
• Long Short-Term Memory

  1997cited by this paper
• An analysis of noise in recurrent neural networks: convergence and generalization

  1996influential reference
• Gradient-based learning algorithms for recurrent networks and their computational complexity

  1995cited by this paper
• Speaker-independent phone recognition using hidden Markov models

  1989cited by this paper

• Do we really need Self-Attention for Streaming Automatic Speech Recognition?

  2026cites this paper
• ViSpeechFormer: A Phonemic Approach for Vietnamese Automatic Speech Recognition

  2026cites this paper
• Chunk-wise Attention Transducers for Fast and Accurate Streaming Speech-to-Text

  2026cites this paper
• Beyond Prompting: Efficient and Robust Contextual Biasing for Speech LLMs via Logit-Space Integration (LOGIC)

  2026cites this paper
• Align-Consistency: Improving Non-autoregressive and Semi-supervised ASR with Consistency Regularization

  2026cites this paper
• A Unified Perspective on CTC and Soft-DTW Using Differentiable DTW

  2026influential citation
• Voxtral Realtime

  2026cites this paper
• VietSuperSpeech: A Large-Scale Vietnamese Conversational Speech Dataset for ASR Fine-Tuning in Chatbot, Customer Support, and Call Center Applications

  2026cites this paper
• NRR-Phi: Text-to-State Mapping for Ambiguity Preservation in LLM Inference

  2026cites this paper
• Categorize Early, Integrate Late: Divergent Processing Strategies in Automatic Speech Recognition

  2026cites this paper
• 823-OLT @ BUET DL Sprint 4.0: Context-Aware Windowing for ASR and Fine-Tuned Speaker Diarization in Bengali Long Form Audio

  2026cites this paper
• Suffix-Constrained Greedy Search Algorithms for Causal Language Models

  2026cites this paper
• Qwen3-ASR Technical Report

  2026cites this paper
• Towards Comprehensive Semantic Speech Embeddings for Chinese Dialects

  2026cites this paper
• Leveraging Beam Search Information for Confidence Estimation in E2E ASR

  2026cites this paper
• Frame-Level Internal Tool Use for Temporal Grounding in Audio LMs

  2026cites this paper
• Fine-tuning Whisper for speech recognition in aquatic product inspection tasks

  2026cites this paper
• Efficient Sparse Selective-Update RNNs for Long-Range Sequence Modeling

  2026cites this paper
• Moonshine v2: Ergodic Streaming Encoder ASR for Latency-Critical Speech Applications

  2026cites this paper
• Relaxing Positional Alignment in Masked Diffusion Language Models

  2026cites this paper
• Typhoon ASR Real-time: FastConformer-Transducer for Thai Automatic Speech Recognition

  2026cites this paper
• IKFST: IOO and KOO Algorithms for Accelerated and Precise WFST-based End-to-End Automatic Speech Recognition

  2026cites this paper
• Sylber 2.0: A Universal Syllable Embedding

  2026influential citation
• TC-BiMamba: Trans-Chunk bidirectionally within BiMamba for unified streaming and non-streaming ASR

  2026cites this paper
• Efficient Dialect-Aware Modeling and Conditioning for Low-Resource Taiwanese Hakka Speech Processing

  2026cites this paper
• 18.2 A 22nm 1.87ms/Frame Streaming Multi-Speaker ASR Accelerator Leveraging Contextual-Aware Redundancy Skipping with 2D-Writable Microscaling Compute-in-Memory and Similarity-Aware TCAM Design

  2026cites this paper
• Fast and General Automatic Differentiation for Finite-State Methods

  2026cites this paper
• Continual test-time dynamic speech recognition via adaptive threshold

  2025cites this paper
• Cautious Next Token Prediction

  2025cites this paper
• Energy-Guided Decoding for Object Hallucination Mitigation

  2025cites this paper
• A Survey of LLM Inference Systems

  2025cites this paper
• Early Attentive Sparsification Accelerates Neural Speech Transcription

  2025cites this paper
• Recent Trends in Distant Conversational Speech Recognition: A Review of CHiME-7 and 8 DASR Challenges

  2025cites this paper
• Autoregressive Speech Enhancement via Acoustic Tokens

  2025cites this paper
• DYNAC: Dynamic Vocabulary based Non-Autoregressive Contextualization for Speech Recognition

  2025cites this paper
• BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models

  2025cites this paper
• Exploring Contextual Knowledge-Enhanced Speech Recognition in Air Traffic Control Communication: A Comparative Study

  2025cites this paper
• Delayed-KD: Delayed Knowledge Distillation based CTC for Low-Latency Streaming ASR

  2025cites this paper
• MFA-KWS: Effective Keyword Spotting With Multi-Head Frame-Asynchronous Decoding

  2025cites this paper
• NGPU-LM: GPU-Accelerated N-Gram Language Model for Context-Biasing in Greedy ASR Decoding

  2025cites this paper
• HENT-SRT: Hierarchical Efficient Neural Transducer with Self-Distillation for Joint Speech Recognition and Translation

  2025cites this paper
• Multi-Hypothesis Distillation of Multilingual Neural Translation Models for Low-Resource Languages

  2025cites this paper
• Customizing a Large Language Model for VHDL Design of High-Performance Microprocessors

  2025cites this paper
• Encoder-Aware Sequence-Level Knowledge Distillation for Low-Resource Neural Machine Translation

  2025cites this paper
• Cross-modal Knowledge Transfer Learning as Graph Matching Based on Optimal Transport for ASR

  2025cites this paper
• TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling

  2025cites this paper
• A study on phonemes recognition method for Mandarin pronunciation based on improved Zipformer-RNN-T(Pruned) modeling

  2025cites this paper
• DuRep: Dual-Mode Speech Representation Learning via ASR-Aware Distillation

  2025cites this paper
• PSRB: A Comprehensive Benchmark for Evaluating Persian ASR Systems

  2025influential citation
• VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining

  2025cites this paper
• Contextualized Automatic Speech Recognition with Dynamic Vocabulary Prediction and Activation

  2025cites this paper
• Running Conventional Automatic Speech Recognition on Memristor Hardware: A Simulated Approach

  2025cites this paper
• WCTC-Biasing: Retraining-free Contextual Biasing ASR with Wildcard CTC-based Keyword Spotting and Inter-layer Biasing

  2025cites this paper
• Pushing the Limits of Beam Search Decoding for Transducer-based ASR models

  2025cites this paper
• Label-Context-Dependent Internal Language Model Estimation for CTC

  2025cites this paper
• Adapting Whisper for Streaming Speech Recognition via Two-Pass Decoding

  2025cites this paper
• Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR

  2025cites this paper
• Enhanced Hybrid Transducer and Attention Encoder Decoder with Text Data

  2025cites this paper
• ASR-Synchronized Speaker-Role Diarization

  2025cites this paper
• INTER: Mitigating Hallucination in Large Vision-Language Models by Interaction Guidance Sampling

  2025cites this paper
• Pronunciation-Lexicon Free Training for Phoneme-Based Crosslingual ASR via Joint Stochastic Approximation

  2025cites this paper
• Mixture of LoRA Experts With Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition

  2025cites this paper
• Forecasting Information Operations with Hybrid Transformer Architecture

  2025cites this paper
• SimulS2S-LLM: Unlocking Simultaneous Inference of Speech LLMs for Speech-to-Speech Translation

  2025cites this paper
• WIND: Accelerated RNN-T Decoding with Windowed Inference for Non-blank Detection

  2025cites this paper
• Multi-modal Streaming ASR in Cross-talk Scenario for Smart Glasses

  2025cites this paper
• Self-Information Guided Speech Segmentation for Efficient Streaming ASR

  2025cites this paper
• Intervening Anchor Token: Decoding Strategy in Alleviating Hallucinations for MLLMs

  2025cites this paper
• Regarding the Existence of the Internal Language Model in CTC-Based E2E ASR

  2025cites this paper
• Open Automatic Speech Recognition Models for Classical and Modern Standard Arabic

  2025cites this paper
• Towards Bringing Parity in Pretraining Datasets for Low-resource Indian Languages

  2025cites this paper
• Toward Real-Time Recognition of Continuous Indian Sign Language: A Multi-Modal Approach Using RGB and Pose

  2025cites this paper
• Generating Long Semantic IDs in Parallel for Recommendation

  2025cites this paper
• Combining multilingual resources to enhance end-to-end speech recognition systems for Scandinavian languages

  2025cites this paper
• LLM Post-Training: A Deep Dive into Reasoning Large Language Models

  2025cites this paper
• Training and Inference Efficiency of Encoder-Decoder Speech Models

  2025cites this paper
• METAL: A Multi-Agent Framework for Chart Generation with Test-Time Scaling

  2025cites this paper
• SegAug: CTC-Aligned Segmented Augmentation For Robust RNN-Transducer Based Speech Recognition

  2025cites this paper
• ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learning

  2025cites this paper
• An Exhaustive Evaluation of TTS- and VC-based Data Augmentation for ASR

  2025cites this paper
• Globally Normalizing the Transducer for Streaming Speech Recognition

  2025influential citation
• Transcribing and Translating, Fast and Slow: Joint Speech Translation and Recognition

  2025cites this paper
• Token-Level Contextual Network with Ladder-Shaped Attention for End-to-End ASR

  2025cites this paper
• Advancing Streaming ASR with Chunk-wise Attention and Trans-chunk Selective State Spaces

  2025cites this paper
• M-MoE: Mixture of Mixture-of-Expert Model for CTC-based Streaming Multilingual ASR

  2025cites this paper
• AMuSE: Attentive Multilingual Speech Encoding for Zero-Prior ASR

  2025cites this paper
• A streaming brain-to-voice neuroprosthesis to restore naturalistic communication

  2025influential citation
• Rate–Distortion–Perception Trade-Off in Information Theory, Generative Models, and Intelligent Communications

  2025cites this paper
• Unsupervised End-to-End Accented Speech Recognition Under Low-Resource Conditions

  2025cites this paper
• LassoRNet: Accurate dim-light melatonin onset time prediction from multiple blood tissue samples

  2025influential citation
• Evaluating Evaluation Metrics - The Mirage of Hallucination Detection

  2025cites this paper
• SpatialReasoner: Towards Explicit and Generalizable 3D Spatial Reasoning

  2025cites this paper
• Beyond the Mode: Sequence-Level Distillation of Multilingual Translation Models for Low-Resource Language Pairs

  2025cites this paper
• Speech-Based Phonetic Transcript Metrics

  2025cites this paper
• Differentiable K-means for Fully-optimized Discrete Token-based ASR

  2025cites this paper
• Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding

  2025cites this paper
• Improving endpoint detection in end-to-end streaming ASR for conversational speech

  2025cites this paper
• Optimal Policy Minimum Bayesian Risk

  2025cites this paper
• Large Language Models for Planning: A Comprehensive and Systematic Survey

  2025cites this paper
• Amulet: ReAlignment During Test Time for Personalized Preference Adaptation of LLMs

  2025cites this paper