Towards Consistent Hybrid HMM Acoustic Modeling

Raissi, Tina; Beck, Eugen; Schlüter, Ralf; Ney, Hermann

doi:10.48550/arxiv.2104.02387

Cited by 3 publications

(3 citation statements)

References 24 publications

(29 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is achieved by a decomposition of the joint label identity of the center phoneme state and its left-right phonemes. With this previous work, and its extension [18], we have shown that it is possible to eliminate the state-tying for the determination of the state inventory, and obtain similar performance to a hybrid CART.…”

Section: Introductionmentioning

confidence: 84%

Improving Factored Hybrid HMM Acoustic Modeling without State Tying

Raissi¹,

Beck²,

Schlüter³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

In this work, we show that a factored hybrid hidden Markov model (FH-HMM) which is defined without any phonetic state-tying outperforms a state-of-the-art hybrid HMM. The factored hybrid HMM provides a link to transducer models in the way it models phonetic (label) context while preserving the strict separation of acoustic and language model of the hybrid HMM approach. Furthermore, we show that the factored hybrid model can be trained from scratch without using phonetic state-tying in any of the training steps. Our modeling approach enables triphone context while avoiding phonetic state-tying by a decomposition into locally normalized factored posteriors for monophones/HMM states in phoneme context. Experimental results are provided for Switchboard 300h and LibriSpeech. On the former task we also show that by avoiding the phonetic state-tying step, the factored hybrid can take better advantage of regularization techniques during training, compared to the standard hybrid HMM with phonetic state-tying based on classification and regression trees (CART).

show abstract

Section: Introductionmentioning

confidence: 84%

Improving Factored Hybrid HMM Acoustic Modeling without State Tying

Raissi¹,

Beck²,

Schlüter³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Also, available pronunciation lexica can be utilized indirectly for assisting subword generation for E2E systems [35], [36], which are shown to outperform byte-pair encoding. Within classical ASR systems, phonetic clustering also can be avoided completely by modeling phonemes in context directly [220].…”

Section: Relationship To Classical Asrmentioning

confidence: 99%

End-to-End Speech Recognition: A Survey

Prabhavalkar,

Hori,

Sainath

et al. 2024

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

In the last decade of automatic speech recognition (ASR) research, the introduction of deep learning has brought considerable reductions in word error rate of more than 50% relative, compared to modeling without deep learning. In the wake of this transition, a number of all-neural ASR architectures have been introduced. These so-called end-to-end (E2E) models provide highly integrated, completely neural ASR models, which rely strongly on general machine learning knowledge, learn more consistently from data, with lower dependence on ASR domainspecific experience. The success and enthusiastic adoption of deep learning, accompanied by more generic model architectures has led to E2E models now becoming the prominent ASR approach. The goal of this survey is to provide a taxonomy of E2E ASR models and corresponding improvements, and to discuss their properties and their relationship to classical hidden Markov model (HMM) based ASR architectures. All relevant aspects of E2E ASR are covered in this work: modeling, training, decoding, and external language model integration, discussions of performance and deployment opportunities, as well as an outlook into potential future developments.

show abstract

“…Also, available pronunciation lexica can be utilized indirectly for assisting subword generation for E2E systems [290], [291], which are shown to outperform byte-pair encoding. Within classical ASR systems, phonetic clustering also can be avoided completely by modeling phonemes in context directly [292].…”

Section: Use Of Large-scale Pretrained Lmsmentioning

confidence: 99%

End-to-End Speech Recognition: A Survey

Prabhavalkar¹,

Hori²,

Sainath³

et al. 2023

Preprint

View full text Add to dashboard Cite

In the last decade of automatic speech recognition (ASR) research, the introduction of deep learning brought considerable reductions in word error rate of more than 50% relative, compared to modeling without deep learning. In the wake of this transition, a number of all-neural ASR architectures were introduced. These so-called end-to-end (E2E) models provide highly integrated, completely neural ASR models, which rely strongly on general machine learning knowledge, learn more consistently from data, while depending less on ASR domainspecific experience. The success and enthusiastic adoption of deep learning accompanied by more generic model architectures lead to E2E models now becoming the prominent ASR approach. The goal of this survey is to provide a taxonomy of E2E ASR models and corresponding improvements, and to discuss their properties and their relation to the classical hidden Markov model (HMM) based ASR architecture. All relevant aspects of E2E ASR are covered in this work: modeling, training, decoding, and external language model integration, accompanied by discussions of performance and deployment opportunities, as well as an outlook into potential future developments.

show abstract

Towards Consistent Hybrid HMM Acoustic Modeling

Cited by 3 publications

References 24 publications

Improving Factored Hybrid HMM Acoustic Modeling without State Tying

Improving Factored Hybrid HMM Acoustic Modeling without State Tying

End-to-End Speech Recognition: A Survey

End-to-End Speech Recognition: A Survey

Contact Info

Product

Resources

About