Provide option to shift formant independently of pitch

rubberband/RubberBandStretcher.h

@@ -421,6 +421,34 @@ public:
      */
     void setPitchScale(double scale);
 
+    /**
+     * Set a pitch scale for the vocal formant envelope separately
+     * from the overall pitch scale.  This is a ratio of target
+     * frequency to source frequency.  For example, a ratio of 2.0
+     * would shift the formant envelope up by one octave; 0.5 down by
+     * one octave; or 1.0 leave the formant unaffected.
+     *
+     * By default this is set to the special value of 0.0, which
+     * causes the scale to be calculated automatically. It will be
+     * treated as 1.0 / the pitch scale if OptionFormantPreserved is
+     * specified, or 1.0 for OptionFormantShifted.
+     *
+     * Conversely, if this is set to a value other than the default
+     * 0.0, formant shifting will happen regardless of the state of
+     * the OptionFormantPreserved/OptionFormantShifted option.
+     *
+     * This function is provided for special effects only. You do not
+     * need to call it for ordinary pitch shifting, with or without
+     * formant preservation - just specify or omit the
+     * OptionFormantPreserved option as appropriate. Use this function
+     * only if you want to shift formants by a distance other than
+     * that of the overall pitch shift.
+     * 
+     * This function is supported only in the R3 (OptionEngineFiner)
+     * engine. It has no effect in R2 (OptionEngineFaster).
+     */
+    void setFormantScale(double scale);
+    
     /**
      * Return the last time ratio value that was set (either on
      * construction or with setTimeRatio()).
@@ -433,6 +461,16 @@ public:
      */
     double getPitchScale() const;
 
+    /**
+     * Return the last formant scaling ratio that was set with
+     * setFormantScale, or 0.0 if the default automatic scaling is in
+     * effect.
+     * 
+     * This function is supported only in the R3 (OptionEngineFiner)
+     * engine. It always returns 0.0 in R2 (OptionEngineFaster).
+     */     
+    double getFormantScale() const;
+    
     /**
      * Return the output delay or latency of the stretcher.  This is
      * the number of audio samples that one would have to discard at

src/RubberBandStretcher.cpp

@@ -75,6 +75,12 @@ RubberBandStretcher::setPitchScale(double scale)
     else m_r3d->setPitchScale(scale);
 }
 
+void
+RubberBandStretcher::setFormantScale(double scale)
+{
+    if (m_r3d) m_r3d->setFormantScale(scale);
+}
+
 double
 RubberBandStretcher::getTimeRatio() const
 {
@@ -89,6 +95,13 @@ RubberBandStretcher::getPitchScale() const
     else return m_r3d->getPitchScale();
 }
 
+double
+RubberBandStretcher::getFormantScale() const
+{
+    if (m_d) return 0.0;
+    else return m_r3d->getFormantScale();
+}
+
 size_t
 RubberBandStretcher::getLatency() const
 {

src/finer/R3StretcherImpl.cpp

@@ -35,6 +35,7 @@ R3StretcherImpl::R3StretcherImpl(Parameters parameters,
     m_parameters(parameters),
     m_timeRatio(initialTimeRatio),
     m_pitchScale(initialPitchScale),
+    m_formantScale(0.0),
     m_guide(Guide::Parameters(m_parameters.sampleRate, parameters.logger)),
     m_guideConfiguration(m_guide.getConfiguration()),
     m_channelAssembly(m_parameters.channels),
@@ -173,6 +174,12 @@ R3StretcherImpl::setPitchScale(double scale)
     calculateHop();
 }
 
+void
+R3StretcherImpl::setFormantScale(double scale)
+{
+    m_formantScale = scale;
+}
+
 void
 R3StretcherImpl::setFormantOption(RubberBandStretcher::Options options)
 {
@@ -233,6 +240,12 @@ R3StretcherImpl::getPitchScale() const
     return m_pitchScale;
 }
 
+double
+R3StretcherImpl::getFormantScale() const
+{
+    return m_formantScale;
+}
+
 size_t
 R3StretcherImpl::getLatency() const
 {
@@ -777,7 +790,9 @@ R3StretcherImpl::adjustFormant(int c)
 
         int highBin = int(floor(fftSize * 10000.0 / m_parameters.sampleRate));
         double targetFactor = double(cd->formant->fftSize) / double(fftSize);
-        double sourceFactor = targetFactor * m_pitchScale;
+        double formantScale = m_formantScale;
+        if (formantScale == 0.0) formantScale = 1.0 / m_pitchScale;
+        double sourceFactor = targetFactor / formantScale;
         double maxRatio = 60.0;
         double minRatio = 1.0 / maxRatio;
 

src/finer/R3StretcherImpl.h

@@ -69,9 +69,11 @@ public:
     
     void setTimeRatio(double ratio);
     void setPitchScale(double scale);
+    void setFormantScale(double scale);
 
     double getTimeRatio() const;
     double getPitchScale() const;
+    double getFormantScale() const;
 
     void setFormantOption(RubberBandStretcher::Options);
     void setPitchOption(RubberBandStretcher::Options);
@@ -265,6 +267,7 @@ protected:
 
     std::atomic<double> m_timeRatio;
     std::atomic<double> m_pitchScale;
+    std::atomic<double> m_formantScale;
     
     std::vector<std::shared_ptr<ChannelData>> m_channelData;
     std::map<int, std::shared_ptr<ScaleData>> m_scaleData;