Text-informed speech enhancement with deep neural networks

By Keisuke Kinoshita, Marc Delcroix, Atsunori Ogawa, Tomohiro Nakatani. 2015

32 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Signal Processing

Citations in the corpus

SpeechX: Neural Codec Language Model as a Versatile Speech Transformer (2023, background): “Furthermore, there has been a lack of comprehensive audio-text-based speech enhancement models that leverage reference transcriptions to generate intelligible speech, except for limited studies focusing only on particular speech enhancement tasks [27], [28].”
Joint Phoneme Alignment and Text-Informed Speech Separation on Highly Corrupted Speech (2020, methodology): “In [6], a sequence of phonemes is forced-aligned with noisy speech and then fed to a deep neural network together with the audio features.”
Speaker-Aware Neural Network Based Beamformer for Speaker Extraction in Speech Mixtures (2017, background): “Note that this work shares similarities with guided speech enhancement approaches which explore incorporating additional knowledge about the sources to improve the enhancement performance [23, 24].”
Speech Enhancement for a Noise-Robust Text-to-Speech Synthesis System Using Deep Recurrent Neural Networks (2016, methodology): “As proposed in [7] we also investigate the use of text-derived features.”
NAUTILUS: A Versatile Voice Cloning System (2020, methodology): “Our proposed system is a multimodal neural network [5], [6], that can be used as TTS [22] or VC [23].”
Speech Enhancement of Noisy and Reverberant Speech for Text-to-Speech (2018, background): “Authors in [7] investigated the use of additional input features derived from the underlying spoken text and found that spectral distortion decreases when text-based features are included.”
Investigating RNN-based speech enhancement methods for noise-robust Text-to-Speech (2016, unknown): “Authors in [7] use text-derived features as an additional input of a feed-forward network that generates enhanced spectrum parameters and found that distortion is smaller when using text.”