Novel Amplitude Scaling method for bilinear frequency Warping-based Voice Conversion

Shah, Nirmesh J.; Patil, Hemant A.

doi:10.1109/icassp.2017.7953212

Cited by 7 publications

(3 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We quantize the parameter α to a set of values within a feasible range [α min , α max ], and consider three ways of forming a region of support: relaxed, intermediate, and strict. It is worth noting that previous efforts on using bilinear frequency warping for VC mostly operate on cepstral features [34]- [35], where a transform matrix is a function of α, but the warping constraint would not form a ROS to define a sparse matrix.…”

Section: B Frequency Warping Constrained Ros Embeddingmentioning

confidence: 99%

Structured Sparse Spectral Transforms and Structural Measures for Voice Conversion

Zhao

Kuruvilla-Dugdale

Song

2018

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

We investigate a structured sparse spectral transform method for voice conversion (VC) to perform frequency warping and spectral shaping simultaneously on high-dimensional (D) STRAIGHT spectra. Learning a large transform matrix for high-D data often results in an overfit matrix with low sparsity, which leads to muffled speech in VC. We address this problem by using the frequency-warping characteristic of a source-target speaker pair to define a region of support (ROS) in a transform matrix, and further optimize it by nonnegative matrix factorization (NMF) to obtain structured sparse transform. We also investigate structural measures of spectral and temporal covariance and variance at different scales for assessing VC speech quality. Our experiments on ARCTIC dataset of 12 speaker pairs show that embedding the ROS in spectral transforms offers flexibility in tradeoffs between spectral distortion and structure preservation, and the structural measures provide quantitatively reasonable results on converted speech. Our subjective listening tests show that the proposed VC method achieves a mean opinion score of "very good" relative to natural speech, and in comparison with three other VC methods, it is the most preferred one in naturalness and in voice similarity to target speakers.

show abstract

Section: B Frequency Warping Constrained Ros Embeddingmentioning

confidence: 99%

Structured Sparse Spectral Transforms and Structural Measures for Voice Conversion

Zhao

Kuruvilla-Dugdale

Song

2018

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

show abstract

“…Here, we propose to use unsupervised Vocal Tract Length Normalization (VTLN)-based warped Gaussian Posteriorgram (GP) features as the speaker-independent representations. Earlier stand-alone VTLN and frequency warpingbased techniques were used in the VC [18,19]. We performed experiments on a small subset of publicly available first Voice Conversion Challenge (VCC) 2016 database [20].…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Vocal Tract Length Warped Posterior Features for Non-Parallel Voice Conversion

2018

View full text Add to dashboard Cite

In the non-parallel Voice Conversion (VC) with the Iterative combination of Nearest Neighbor search step and Conversion step Alignment (INCA) algorithm, the occurrence of one-tomany and many-to-one pairs in the training data will deteriorate the performance of the stand-alone VC system. The work on handling these pairs during the training is less explored. In this paper, we establish the relationship via intermediate speaker-independent posteriorgram representation, instead of directly mapping the source spectrum to the target spectrum. To that effect, a Deep Neural Network (DNN) is used to map the source spectrum to posteriorgram representation and another DNN is used to map this posteriorgram representation to the target speaker's spectrum. In this paper, we propose to use unsupervised Vocal Tract Length Normalization (VTLN)based warped Gaussian posteriorgram features as the speakerindependent representations. We performed experiments on a small subset of publicly available Voice Conversion Challenge (VCC) 2016 database. We obtain the lower Mel Cepstral Distortion (MCD) values with the proposed approach compared to the baseline as well as the supervised phonetic posteriorgram feature-based speaker-independent representations. Furthermore, subjective evaluation gave relative improvement of 13.3 % with the proposed approach in terms of Speaker Similarity (SS).

show abstract

“…VC broadly can be categorized into parallel (if both the speakers have spoken the same utterances) and non-parallel cases (if both the speakers have spoken different utterances from a same language or different language). Stand-alone VC techniques that are based on Gaussian Mixture Model (GMM) [2,3], frequency warping (FW) [4,5], exemplar [6] and Deep Neural Network (DNN) [7][8][9] requires the aligned spectral features before learning the mapping function. In the VC literature, it has been shown that the alignment accuracy clearly affects the quality of converted speech signal [10][11][12].…”

Section: Introductionmentioning

confidence: 99%

Effectiveness of Dynamic Features in INCA and Temporal Context-INCA

Shah

Patil

2018

Interspeech 2018

View full text Add to dashboard Cite

Non-parallel Voice Conversion (VC) has gained significant attention since last one decade. Obtaining corresponding speech frames from both the source and target speakers before learning the mapping function in the non-parallel VC is a key step in the standalone VC task. Obtaining such corresponding pairs, is more challenging due to the fact that both the speakers may have uttered different utterances from same or the different languages. Iterative combination of a Nearest Neighbor search step and a Conversion step Alignment (INCA) and its variant Temporal Context (TC)-INCA are popular unsupervised alignment algorithms. The INCA and TC-INCA iteratively learn the mapping function after getting the Nearest Neighbor (NN) aligned pairs from the intermediate converted and the target spectral features. In this paper, we propose to use dynamic features along with static features to calculate the NN aligned pairs in both the INCA and TC-INCA algorithms (since the dynamic features are known to play a key role to differentiate major phonetic categories). We obtained on an average relative improvement of 13.75 % and 5.39 % with our proposed Dynamic INCA and Dynamic TC-INCA, respectively. This improvement is also positively reflected in the quality of converted voices.

show abstract

Novel Amplitude Scaling method for bilinear frequency Warping-based Voice Conversion

Cited by 7 publications

References 25 publications

Structured Sparse Spectral Transforms and Structural Measures for Voice Conversion

Structured Sparse Spectral Transforms and Structural Measures for Voice Conversion

Unsupervised Vocal Tract Length Warped Posterior Features for Non-Parallel Voice Conversion

Effectiveness of Dynamic Features in INCA and Temporal Context-INCA

Contact Info

Product

Resources

About